You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/03/09 07:22:17 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@6b4e3d08ea0155dad5a04272e196b18b3725150b)
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 fdf449e2f8 deploying docs (apache/tvm@6b4e3d08ea0155dad5a04272e196b18b3725150b)
fdf449e2f8 is described below
commit fdf449e2f8814a8205e8f4bd9ed8880b64b742ad
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Mar 9 07:22:10 2023 +0000
deploying docs (apache/tvm@6b4e3d08ea0155dad5a04272e196b18b3725150b)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 312563 -> 333957 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22858 -> 23827 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_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1140 ++++----------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 91 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 483 +++------
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 61 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 10 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 43 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
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 | 1140 ++++----------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 91 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 483 +++------
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
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 +-
docs/reference/api/typedoc/classes/instance.html | 58 +-
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 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../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 | 124 +--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 273 ++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 18 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
130 files changed, 1805 insertions(+), 3310 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 793f3e36e6..b0c19c3436 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 94f0e4545f..475ea5ff8a 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 7936bd66a8..0a37998dc0 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.209 seconds)
+ **Total running time of the script:** ( 1 minutes 22.704 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 bf81554e3c..91bdc62360 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ 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 965ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 1s/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 7296e0a862..69a6af1415 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip13064ef0-01fe-40c0-8830-31cc39add181 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipd677e57f-ec27-4d38-b579-f935463c05f8 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 32bcf4cc9e..8d0bcd81d2 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ 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]
6%|6 | 2.66M/41.5M [00:00<00:02, 19.7MB/s]
19%|#9 | 7.99M/41.5M [00:00<00:01, 30.9MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 39.0MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 42.9MB/s]
64%|######3 | 26.4M/41.5M [00:00<00:00, 41.1MB/s]
82%|########2 | 34.1M/41.5M [00:01<00:00, 33.2MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 34.0MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 36.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
17%|#6 | 6.89M/41.5M [00:00<00:00, 72.2MB/s]
33%|###3 | 13.8M/41.5M [00:00<00:00, 61.1MB/s]
48%|####7 | 19.7M/41.5M [00:00<00:00, 36.9MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 38.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 48.1MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 42.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 44.9MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 996c057916..9df572e4ef 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
55%|#####4 | 24.4M/44.7M [00:00<00:00, 72.0MB/s]
99%|#########8| 44.0M/44.7M [00:00<00:00, 115MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 93.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 54.9MB/s]
36%|###6 | 16.1M/44.7M [00:00<00:00, 69.3MB/s]
54%|#####3 | 24.1M/44.7M [00:00<00:00, 75.3MB/s]
76%|#######6 | 34.1M/44.7M [00:00<00:00, 78.6MB/s]
93%|#########3| 41.7M/44.7M [00:00<00:00, 76.2MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 77.7MB/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 197e28d3ec..496f85c177 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 25.418 seconds)
+ **Total running time of the script:** ( 1 minutes 26.975 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 ddd5dff757..d18ce32f81 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
=================
-**06:42.715** total execution time for **how_to_compile_models** files:
+**06:57.081** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:25.418 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:26.975 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:20.209 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:22.704 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:55.879 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:59.988 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.679 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:40.374 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.081 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:33.401 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.934 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.895 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.667 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.824 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.213 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:27.111 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.937 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:24.022 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.697 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.788 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 355b26a8b0..31bfd83fcc 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -727,7 +727,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2679.2213 2677.6973 2684.0391 2676.3311 2.7731
+ 2680.9920 2680.4620 2684.3987 2679.0878 1.7751
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 052bd1ec21..359c312cf0 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
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7123 15.6223 16.2050 15.5184 0.2118
+ 16.3294 16.3073 16.5066 16.1819 0.1016
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 c0f32ceeeb..cf962af989 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
@@ -130,7 +130,7 @@ 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]
4%|4 | 6.83M/170M [00:00<00:02, 71.6MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 67.4MB/s]
13%|#3 | 22.5M/170M [00:00<00:02, 63.5MB/s]
17%|#6 | 28.5M/170M [00:00<00:02, 52.9MB/s]
22%|##2 | 37.7M/170M [00:00<00:02, 65.5MB/s]
28%|##7 | 47.4M/170M [00:00<00:01, 76.3MB/s]
32%|###2 | 55.1M/170M [00:00<00:01, 74.8MB/s]
38%|###7 | 64.0M/170M [00:00<00:01, 71.9MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 70.8MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 71.8MB/s]
52%|#####1 | 87.7M/170M [00:01<00:01, 74.2MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 73.0MB/s]
61%|######1 | 104M/170M [00:01<00:01, 63.3MB/s]
66%|######6 | 113M/170M [00:01<00:00, 70.7MB/s]
74%|#######3 | 125M/170M [00:01<00:00, 85.6MB/s]
79%|#######8 | 134M/170M [00:01<00:00, 86.3MB/s]
84%|########3 | 142M/170M [00:02<00:00, 82.1MB/s]
89%|########9 | 152M/170M [00:02<00:00, 79.2MB/s]
95%|#########4| 161M/170M [00:02<00:00, 82.5MB/s]
100%|##########| 170M/170M [00:02<00:00, 75.8MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 64.3MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 54.9MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 59.2MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 54.2MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 61.9MB/s]
28%|##8 | 48.0M/170M [00:00<00:01, 67.2MB/s]
33%|###2 | 56.0M/170M [00:00<00:01, 71.5MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 68.3MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 66.6MB/s]
48%|####8 | 81.7M/170M [00:01<00:01, 75.8MB/s]
53%|#####2 | 89.2M/170M [00:01<00:01, 76.4MB/s]
57%|#####6 | 96.7M/170M [00:01<00:01, 57.5MB/s]
63%|######2 | 106M/170M [00:01<00:00, 67.2MB/s]
67%|######7 | 114M/170M [00:01<00:00, 71.6MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 70.3MB/s]
76%|#######6 | 129M/170M [00:02<00:00, 72.1MB/s]
81%|########1 | 138M/170M [00:02<00:00, 74.4MB/s]
88%|########8 | 150M/170M [00:02<00:00, 87.3MB/s]
93%|#########3| 158M/170M [00:02<00:00, 61.2MB/s]
97%|#########7| 165M/170M [00:02<00:00, 57.4MB/s]
100%|##########| 170M/170M [00:02<00:00, 65.5MB/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').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 29.941 seconds)
+ **Total running time of the script:** ( 3 minutes 57.575 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 dc6f6793e3..690ff0dfdf 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 74.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 78.2MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 35.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 49.8MB/s]
@@ -409,7 +409,7 @@ 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)
- 90.1262 90.1053 90.8286 89.7640 0.2328
+ 90.3788 90.2946 92.4767 90.1564 0.3383
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.605 seconds)
+ **Total running time of the script:** ( 1 minutes 21.495 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 99f38ddace..52cbea00b7 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
@@ -423,7 +423,7 @@ 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)
- 119.3569 119.4587 120.4381 115.8352 0.7321
+ 122.3517 122.2107 127.3617 121.4043 0.7275
@@ -460,7 +460,7 @@ 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 28.628 seconds)
+ **Total running time of the script:** ( 2 minutes 36.166 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 455e224016..4baacc3af4 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 39.698 seconds)
+ **Total running time of the script:** ( 1 minutes 43.525 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 ebd7b50864..71c796681c 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
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 1129/132723 [00:00<00:11, 11160.32KB/s]
3%|2 | 3478/132723 [00:00<00:07, 18377.73KB/s]
6%|5 | 7417/132723 [00:00<00:04, 27902.28KB/s]
11%|# | 14009/132723 [00:00<00:02, 42868.67KB/s]
17%|#7 | 22679/132723 [00:00<00:01, 58646.85KB/s]
24%|##3 | 31423/132723 [00:00<00:01, 68423.43KB/s]
30%|### | 40148/132723 [00:00<00:01, 74571.75KB/s]
37%|###6 | 48912/132723 [00:00<00:01, 78727.23KB/s]
43%|####3 | 57649/132723 [00:00<00:00, 81424.64KB/s]
50%|####9 | 65794/132723 [00:01<00:00, 75145.68KB/s]
56%|#####6 | 74576/132723 [00:01<00:00, 78809.10KB/s]
62%|######2 | 82544/132723 [00:01<00:00, 62226.50KB/s]
69%|######8 | 91278/132723 [00:01<00:00, 68437.78KB/s]
74%|#######4 | 98666/132723 [00:01<00:00, 65354.91KB/s]
81%|######## | 107375/132723 [00:01<00:00, 70975.71KB/s]
87%|########6 |
114836/132723 [00:01<00:00, 62718.45KB/s]
93%|#########3| 123563/132723 [00:01<00:00, 68891.99KB/s]
100%|#########9| 132419/132723 [00:02<00:00, 74088.62KB/s]
100%|##########| 132723/132723 [00:02<00:00, 66094.37KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6667/132723 [00:00<00:01, 66660.21KB/s]
11%|#1 | 15213/132723 [00:00<00:01, 77709.57KB/s]
17%|#7 | 23089/132723 [00:00<00:01, 78184.78KB/s]
24%|##3 | 31735/132723 [00:00<00:01, 81449.95KB/s]
30%|### | 40354/132723 [00:00<00:01, 83155.44KB/s]
37%|###6 | 49007/132723 [00:00<00:00, 84300.13KB/s]
43%|####3 | 57691/132723 [00:00<00:00, 85119.50KB/s]
50%|##### | 66442/132723 [00:00<00:00, 85877.05KB/s]
57%|#####6 | 75161/132723 [00:00<00:00, 86286.32KB/s]
63%|######3 | 83790/132723 [00:01<00:00, 85666.83KB/s]
70%|######9 | 92493/132723 [00:01<00:00, 86079.31KB/s]
76%|#######6 | 101232/132723 [00:01<00:00, 86474.02KB/s]
83%|########2 | 109915/132723 [00:01<00:00, 86574.76KB/s]
89%|########9 | 118630/132723 [00:01<00:00, 86746.35KB/s]
96%|#########5| 127307/132723 [00:01<00:00, 86744.53KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84701.86KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 49.677 seconds)
+ **Total running time of the script:** ( 3 minutes 58.707 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 c0922f63f4..d4b244261a 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**15:19.269** total execution time for **how_to_deploy_models** files:
+**16:19.020** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:49.677 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:58.707 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:29.941 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:57.575 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.628 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:36.166 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:39.698 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:43.525 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.605 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:21.495 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.267 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:58.395 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.796 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:45.109 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.051 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:29.140 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.601 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.901 | 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 71a9aa844a..e99279effa 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
@@ -463,7 +463,7 @@ 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.zip914073f8-611c-444e-aff3-34937d89d68b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip94ac835c-f995-4cb0-b2f7-877771d9ffcf 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 a2c71adcff..e1e5704c51 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
=================
-**00:55.751** total execution time for **how_to_extend_tvm** files:
+**00:58.857** 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``) | 00:51.808 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:54.633 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.819 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:03.023 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.191 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.009 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.010 | 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 bd1c66b73e..6f4b7f99a6 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
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 22758us [22758us] (49.17%; 49.17%)
- FoldScaleAxis: 23528us [9us] (50.83%; 50.83%)
- FoldConstant: 23519us [1800us] (50.81%; 99.96%)
- InferType: 21719us [21719us] (46.92%; 92.35%)
+ InferType: 23430us [23430us] (48.59%; 48.59%)
+ FoldScaleAxis: 24786us [10us] (51.41%; 51.41%)
+ FoldConstant: 24776us [1908us] (51.39%; 99.96%)
+ InferType: 22868us [22868us] (47.43%; 92.30%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 21886us [21886us] (48.37%; 48.37%)
- FoldScaleAxis: 23357us [6us] (51.63%; 51.63%)
- FoldConstant: 23351us [1734us] (51.61%; 99.97%)
- InferType: 21617us [21617us] (47.78%; 92.58%)
+ InferType: 23996us [23996us] (49.21%; 49.21%)
+ FoldScaleAxis: 24771us [10us] (50.79%; 50.79%)
+ FoldConstant: 24761us [1957us] (50.77%; 99.96%)
+ InferType: 22804us [22804us] (46.76%; 92.10%)
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 fa171d6f00..1d1423168d 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
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 49.179840 ms
+ Convolution: 51.304000 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 2bc82b0cc9..c9e67891cb 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
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 9.528096 ms
+ conv2d with tensor core: 13.327136 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 f4cf7eff5b..63442e83c7 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018623
- Baseline: 3.480098
+ Numpy running time: 0.019816
+ Baseline: 3.548278
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.312424
+ Opt1: 0.341101
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.341044
+ Opt2: 0.362876
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116375
+ Opt3: 0.134954
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108872
+ Opt4: 0.111578
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111690
+ Opt5: 0.112967
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147042
+ Opt6: 0.149115
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 9dba7507d1..ec90dae145 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.456** total execution time for **how_to_optimize_operators** files:
+**00:36.800** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.674 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:34.133 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.612 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.574 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.170 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.093 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index a35cceb65f..3f2e3cfbc2 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
=================
-**09:54.087** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:13.968** 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``) | 06:02.332 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:14.515 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:42.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:47.121 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:08.047 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:09.481 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.574 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:33.824 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.473 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.704 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:14.092 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:14.323 | 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 9901657108..c4dc568f9a 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
@@ -244,11 +244,11 @@ cooperative fetching, unrolling and operator fusion.
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.launch_thread("blockIdx.x", 16)
- conv2d_nchw = T.allocate([7], "float32", "local")
- pad_temp_shared = T.allocate([2592], "float32", "shared")
- kernel_shared = T.allocate([9216], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 224)
- conv2d_nchw_1 = T.Buffer((1,), data=conv2d_nchw, scope="local", align=4)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([324], "float32", "shared")
+ kernel_shared = T.allocate([1152], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 112)
+ conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
@@ -256,453 +256,124 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
- for rc_outer_outer in range(16):
- cse_var_2: T.int32 = rc_outer_outer * 1568
- cse_var_1: T.int32 = rc_outer_outer * 288
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer in range(128):
+ cse_var_2: T.int32 = rc_outer_outer * 196
+ cse_var_1: T.int32 = rc_outer_outer * 36
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((2592,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((324,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 224):
+ with T.launch_thread(threadIdx_x_1, 112):
pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(9 <= (threadIdx_x_1 + 43) % 81 and (threadIdx_x_1 + 43) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 81 * 49 + (threadIdx_x_1 + 43) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 672] = T.if_then_else(9 <= (threadIdx_x_1 + 24) % 81 and (threadIdx_x_1 + 24) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 672) // 81 * 49 + (threadIdx_x_1 + 24) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 896] = T.if_then_else(9 <= (threadIdx_x_1 + 5) % 81 and (threadIdx_x_1 + 5) % 81 < 72 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 896) // 81 * 49 + (threadIdx_x_1 + 5) % 81 // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1120] = T.if_then_else(9 <= (threadIdx_x_1 + 67) % 81 and (threadIdx_x_1 + 67) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1120) // 81 * 49 + (threadIdx_x_1 + 67) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1344] = T.if_then_else(9 <= (threadIdx_x_1 + 48) % 81 and (threadIdx_x_1 + 48) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1344) // 81 * 49 + (threadIdx_x_1 + 48) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(9 <= (threadIdx_x_1 + 29) % 81 and (threadIdx_x_1 + 29) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 81 * 49 + (threadIdx_x_1 + 29) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1792] = T.if_then_else(9 <= (threadIdx_x_1 + 10) % 81 and (threadIdx_x_1 + 10) % 81 < 72 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1792) // 81 * 49 + (threadIdx_x_1 + 10) % 81 // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 2016] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 8) % 9 and (threadIdx_x_1 + 72) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2016) // 81 * 49 + (threadIdx_x_1 // 9 + 8) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 2240] = T.if_then_else(9 <= (threadIdx_x_1 + 53) % 81 and (threadIdx_x_1 + 53) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2240) // 81 * 49 + (threadIdx_x_1 + 53) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- if T.likely(threadIdx_x_1 < 128):
- pad_temp_shared_1[threadIdx_x_1 + 2464] = T.if_then_else(9 <= (threadIdx_x_1 + 34) % 81 and (threadIdx_x_1 + 34) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2464) // 81 * 49 + (threadIdx_x_1 + 34) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(9 <= (threadIdx_x_1 + 31) % 81 and (threadIdx_x_1 + 31) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ if T.likely(threadIdx_x_1 < 100):
+ pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((9216,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((1152,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 224):
- kernel_shared_1[threadIdx_x_2 * 16] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16]
- kernel_shared_1[threadIdx_x_2 * 16 + 1] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 1]
- kernel_shared_1[threadIdx_x_2 * 16 + 2] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 2]
- kernel_shared_1[threadIdx_x_2 * 16 + 3] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 3]
- kernel_shared_1[threadIdx_x_2 * 16 + 4] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 4]
- kernel_shared_1[threadIdx_x_2 * 16 + 5] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 5]
- kernel_shared_1[threadIdx_x_2 * 16 + 6] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 6]
- kernel_shared_1[threadIdx_x_2 * 16 + 7] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 7]
- kernel_shared_1[threadIdx_x_2 * 16 + 8] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 8]
- kernel_shared_1[threadIdx_x_2 * 16 + 9] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 9]
- kernel_shared_1[threadIdx_x_2 * 16 + 10] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 10]
- kernel_shared_1[threadIdx_x_2 * 16 + 11] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 11]
- kernel_shared_1[threadIdx_x_2 * 16 + 12] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 12]
- kernel_shared_1[threadIdx_x_2 * 16 + 13] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 13]
- kernel_shared_1[threadIdx_x_2 * 16 + 14] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 14]
- kernel_shared_1[threadIdx_x_2 * 16 + 15] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 15]
- with T.launch_thread(threadIdx_x_2, 224):
- kernel_shared_1[threadIdx_x_2 * 16 + 3584] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 128) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3585] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 129) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3586] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 130) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3587] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 131) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3588] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 132) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3589] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 133) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3590] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 134) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3591] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 135) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3592] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 136) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3593] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 137) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3594] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 138) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3595] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 139) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3596] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 140) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3597] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 141) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3598] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 142) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3599] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 143) % 288]
- with T.launch_thread(threadIdx_x_2, 224):
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7168] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 256) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7169] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 257) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7170] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 258) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7171] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 259) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7172] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 260) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7173] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 261) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7174] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 262) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7175] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 263) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7176] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 264) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7177] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 265) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7178] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 266) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7179] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 267) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7180] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 268) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7181] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 269) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7182] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 270) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7183] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 271) % 288]
- for rc_outer_inner, rx_outer_inner in T.grid(2, 3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 144] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 144] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 153] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 162] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 171] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 171] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 225] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 225] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 234] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 243] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 306] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 306] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 324] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 333] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 333] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 387] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 387] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 396] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 405] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 414] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 414] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 468] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 468] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 477] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 486] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 495] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 513] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 522] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 531] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 540] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 495] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 513] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 522] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 531] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 540] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 549] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 513] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 522] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 531] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 540] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 549] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 558] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 576] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 585] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 594] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 603] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 612] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 621] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 576] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 585] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 594] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 603] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 612] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 621] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 585] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 594] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 603] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 612] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 621] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 639] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 648] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 657] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 666] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 675] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 684] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 702] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 657] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 666] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 675] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 684] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 702] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 711] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 666] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 675] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 684] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 702] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 711] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 720] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 729] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 738] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 747] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 765] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 774] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 783] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 738] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 747] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 765] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 774] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 783] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 792] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 747] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 765] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 774] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 783] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 792] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 801] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 810] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 828] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 837] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 846] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 855] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 864] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 828] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 837] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 846] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 855] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 864] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 873] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 828] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 837] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 846] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 855] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 864] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 873] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 891] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 900] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 909] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 918] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 927] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 936] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 900] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 909] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 918] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 927] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 936] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 954] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 909] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 918] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 927] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 936] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 954] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 963] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 972] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 981] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 990] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 999] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1017] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1026] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 981] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 990] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 999] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1017] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1026] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1035] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 990] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 999] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1017] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1026] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1035] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1044] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1053] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1062] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1080] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1089] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1098] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1107] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1062] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1080] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1089] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1098] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1107] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1116] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1080] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1089] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1098] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1107] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1116] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1125] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1143] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1152] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1161] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1170] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1179] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1188] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1143] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1152] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1161] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1170] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1179] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1188] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1152] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1161] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1170] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1179] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1188] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1206] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1215] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1224] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1233] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1242] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1251] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1269] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1224] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1233] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1242] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1251] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1269] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1278] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1233] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1242] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1251] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1269] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1278] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1287] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- compute_1 = T.Buffer((25088,), data=compute.data)
- bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7] = T.max(conv2d_nchw_1[0] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 7] = T.max(conv2d_nchw_1[1] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 14] = T.max(conv2d_nchw_1[2] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 21] = T.max(conv2d_nchw_1[3] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 28] = T.max(conv2d_nchw_1[4] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 35] = T.max(conv2d_nchw_1[5] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 42] = T.max(conv2d_nchw_1[6] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 2]
+ kernel_shared_1[threadIdx_x_2 * 2 + 1] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 2 + 1]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 224] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 112) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 225] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 112) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 9) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 448] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 449] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 17) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 672] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 336) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 24) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 673] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 336) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 25) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 896] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 32) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 897] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 33) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ if T.likely(threadIdx_x_2 < 16):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1120] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 560) // 18 * 4608 + cse_var_1 + threadIdx_x_2 * 2 + 4]
+ if T.likely(threadIdx_x_2 < 16):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1121] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 560) // 18 * 4608 + cse_var_1 + threadIdx_x_2 * 2 + 5]
+ for rc_outer_inner, ff_outer_inner, rc_inner in T.grid(2, 2, 2):
+ cse_var_9: T.int32 = ff_outer_inner * 7
+ cse_var_8: T.int32 = cse_var_9 + 6
+ cse_var_7: T.int32 = cse_var_9 + 5
+ cse_var_6: T.int32 = cse_var_9 + 4
+ cse_var_5: T.int32 = cse_var_9 + 3
+ cse_var_4: T.int32 = cse_var_9 + 2
+ cse_var_3: T.int32 = cse_var_9 + 1
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ for i1_inner, i2_inner in T.grid(2, 7):
+ compute_1 = T.Buffer((25088,), data=compute.data)
+ bias_1 = T.Buffer((512,), data=bias.data)
+ compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner * 7 + i2_inner] + bias_1[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
@@ -752,7 +423,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.235 ms
+ Execution time of this operator: 0.298 ms
@@ -801,33 +472,33 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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_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=32)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
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_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=32)
+ 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=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
- compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=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=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
@@ -847,16 +518,16 @@ 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=16)
+ 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=2)
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=224)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
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=224)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -874,10 +545,10 @@ 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__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[9216];
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -885,451 +556,112 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((9 <= ((((int)threadIdx.x) + 10) % 81)) && (((((int)threadIdx.x) + 10) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + ((((((int)threadIdx.x) + 10) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 128) {
- pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 100) {
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
}
- kernel_shared[(((int)threadIdx.x) * 16)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16))];
- kernel_shared[((((int)threadIdx.x) * 16) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 16) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 16) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 3)];
- kernel_shared[((((int)threadIdx.x) * 16) + 4)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 4)];
- kernel_shared[((((int)threadIdx.x) * 16) + 5)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 5)];
- kernel_shared[((((int)threadIdx.x) * 16) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 6)];
- kernel_shared[((((int)threadIdx.x) * 16) + 7)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 7)];
- kernel_shared[((((int)threadIdx.x) * 16) + 8)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 8)];
- kernel_shared[((((int)threadIdx.x) * 16) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 9)];
- kernel_shared[((((int)threadIdx.x) * 16) + 10)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 10)];
- kernel_shared[((((int)threadIdx.x) * 16) + 11)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 11)];
- kernel_shared[((((int)threadIdx.x) * 16) + 12)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 12)];
- kernel_shared[((((int)threadIdx.x) * 16) + 13)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 13)];
- kernel_shared[((((int)threadIdx.x) * 16) + 14)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 14)];
- kernel_shared[((((int)threadIdx.x) * 16) + 15)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 15)];
- kernel_shared[((((int)threadIdx.x) * 16) + 3584)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 128) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3585)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 129) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3586)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 130) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3587)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 131) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3588)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 132) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3589)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 133) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3590)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 134) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3591)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 135) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3592)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 136) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3593)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 137) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3594)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 138) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3595)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 139) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3596)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 140) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3597)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 141) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3598)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 142) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3599)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 143) % 288))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7168)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 256) % 288))];
+ kernel_shared[(((int)threadIdx.x) * 2)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 18) * 2))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 18) * 2)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 2) + 224)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 8) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 225)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 9) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 448)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 16) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 449)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 17) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 672)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 24) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 673)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 25) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 896)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 32) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 897)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 33) % 36))];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 2) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) * 2)) + 4)];
}
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7169)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 257) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7170)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 258) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7171)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 259) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7172)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 260) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7173)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 261) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7174)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 262) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7175)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 263) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7176)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 264) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7177)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 265) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7178)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 266) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7179)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 267) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7180)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 268) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7181)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 269) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7182)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 270) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7183)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 271) % 288))];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 2) + 1121)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) * 2)) + 5)];
}
__syncthreads();
for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1035)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1035)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1044)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1116)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1116)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1125)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1206)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1278)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1278)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1287)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ }
}
}
}
- compute[(((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
+ }
}
@@ -1388,7 +720,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 2.332 seconds)
+ **Total running time of the script:** ( 6 minutes 14.515 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 0dcd07094b..d97fe0f20e 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
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8959 7.8996 7.9098 7.8783 0.0131
+ 7.8876 7.8866 7.8967 7.8795 0.0070
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.047 seconds)
+ **Total running time of the script:** ( 1 minutes 9.481 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 cbe84d2810..31ccc225ac 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
@@ -666,7 +666,7 @@ 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)
- 748.7372 748.0161 750.2849 747.9105 1.0953
+ 757.5129 755.1987 762.1745 755.1656 3.2962
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 42.569 seconds)
+ **Total running time of the script:** ( 1 minutes 47.121 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 f7bc235348..c9132c9f8a 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
@@ -389,26 +389,75 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_outer_inner, nb_j_inner in T.grid(8, 2):
- for i_inner_init, j_init in T.grid(4, 16):
- compute_2[i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 4, 16):
- cse_var_1 = T.int32()
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_2: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16 + j
- placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
- placeholder_7 = T.Buffer((32768,), data=placeholder.data)
- placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 8192 + i_outer_inner * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner in range(32):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
- compute_3 = T.Buffer((65536,), data=compute.data)
- placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
+ for i0_outer in T.parallel(2):
+ compute_1 = T.allocate([2048], "float32", "global")
+ for i1_outer in range(16):
+ compute_2 = T.Buffer((2048,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(16, 2):
+ for i_inner_init in range(4):
+ cse_var_1: T.int32 = i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16
+ compute_2[cse_var_1] = T.float32(0)
+ compute_2[cse_var_1 + 1] = T.float32(0)
+ compute_2[cse_var_1 + 2] = T.float32(0)
+ compute_2[cse_var_1 + 3] = T.float32(0)
+ compute_2[cse_var_1 + 4] = T.float32(0)
+ compute_2[cse_var_1 + 5] = T.float32(0)
+ compute_2[cse_var_1 + 6] = T.float32(0)
+ compute_2[cse_var_1 + 7] = T.float32(0)
+ compute_2[cse_var_1 + 8] = T.float32(0)
+ compute_2[cse_var_1 + 9] = T.float32(0)
+ compute_2[cse_var_1 + 10] = T.float32(0)
+ compute_2[cse_var_1 + 11] = T.float32(0)
+ compute_2[cse_var_1 + 12] = T.float32(0)
+ compute_2[cse_var_1 + 13] = T.float32(0)
+ compute_2[cse_var_1 + 14] = T.float32(0)
+ compute_2[cse_var_1 + 15] = T.float32(0)
+ for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i1_outer * 2 + nb_j_inner}), 4):
+ cse_var_2 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i1_outer * 2 + nb_j_inner
+ cse_var_19: T.int32 = i0_outer * 16384 + i_outer_inner * 1024 + i_inner * 256
+ cse_var_18: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16
+ cse_var_17: T.int32 = cse_var_18 + 9
+ cse_var_16: T.int32 = cse_var_18 + 8
+ cse_var_15: T.int32 = cse_var_18 + 7
+ cse_var_14: T.int32 = cse_var_18 + 6
+ cse_var_13: T.int32 = cse_var_18 + 5
+ cse_var_12: T.int32 = cse_var_18 + 4
+ cse_var_11: T.int32 = cse_var_18 + 3
+ cse_var_10: T.int32 = cse_var_18 + 2
+ cse_var_9: T.int32 = cse_var_18 + 15
+ cse_var_8: T.int32 = cse_var_18 + 14
+ cse_var_7: T.int32 = cse_var_18 + 13
+ cse_var_6: T.int32 = cse_var_18 + 12
+ cse_var_5: T.int32 = cse_var_18 + 11
+ cse_var_4: T.int32 = cse_var_18 + 10
+ cse_var_3: T.int32 = cse_var_18 + 1
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(64, 32):
+ cse_var_22: T.int32 = i0_outer * 32768 + i0_inner * 512 + i1_outer * 32 + i1_inner
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ compute_3[cse_var_22] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_22], T.float32(0))
@@ -458,7 +507,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.460 ms
+ Execution time of this operator: 1.964 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 d5e240196b..37f6fcf7f6 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:46.686** total execution time for **how_to_tune_with_autotvm** files:
+**00:48.473** 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``) | 00:46.650 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:48.437 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.004 | 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 bf3a3a1b75..70619c1757 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
@@ -390,7 +390,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9319783
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8828472
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -513,8 +513,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1855297
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1329391
+ No: 3 GFLOPS: 101.53/101.53 result: MeasureResult(costs=(0.0022801618679245284,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8529009819030762, timestamp=1678344053.1014893) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3307932
+ No: 4 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -636,26 +637,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7875377
- No: 4 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, 32, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8726377
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1410168
+ No: 5 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -777,8 +760,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5546995
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10372282
+ No: 6 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -900,9 +883,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8929719
- No: 7 GFLOPS: 5.45/5.45 result: MeasureResult(costs=(0.042468505749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.280545949935913, timestamp=1678321445.854263) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3693244
- No: 8 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10348246
+ No: 7 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1024,8 +1006,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3447303
- No: 9 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4784229
+ No: 8 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1147,131 +1129,161 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6836343
- No: 10 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2068700
+ No: 9 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+ During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007fbd9826cfa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h:1621
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2769782
- No: 11 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
+
+ Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7944121
+ No: 10 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1393,8 +1405,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4146053
- No: 12 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1569880
+ No: 11 GFLOPS: 37.54/101.53 result: MeasureResult(costs=(0.006166648411764706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3040320873260498, timestamp=1678344066.3975585) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,655438
+ No: 12 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1516,8 +1529,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6141551
- No: 13 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7151729
+ No: 13 GFLOPS: 3.89/101.53 result: MeasureResult(costs=(0.05952210225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.798225402832031, timestamp=1678344075.3766592) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9298467
+ No: 14 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1639,8 +1653,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6546831
- No: 14 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,792053
+ No: 15 GFLOPS: 77.32/101.53 result: MeasureResult(costs=(0.0029941216226415097,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.99426531791687, timestamp=1678344076.4028218) [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8917302
+ No: 16 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1762,8 +1777,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3347534
- No: 15 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5606092
+ No: 17 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1885,163 +1900,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5237374
- No: 16 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f2ef633ffa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
- Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4685999
- No: 17 GFLOPS: 110.53/110.53 result: MeasureResult(costs=(0.0020944786041666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.464320421218872, timestamp=1678321455.9058175) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2332914
- No: 18 GFLOPS: 5.84/110.53 result: MeasureResult(costs=(0.0396171035,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.570124864578247, timestamp=1678321456.8276098) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1675584
- No: 19 GFLOPS: 0.00/110.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5634724
+ No: 18 GFLOPS: 3.96/101.53 result: MeasureResult(costs=(0.058526657,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.256460189819336, timestamp=1678344078.8579617) [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5818500
+ No: 19 GFLOPS: 2.69/101.53 result: MeasureResult(costs=(0.08609279625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1326193809509277, timestamp=1678344080.4110823) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,36280
+ No: 20 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2163,8 +2025,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2690307
- No: 20 GFLOPS: 70.03/110.53 result: MeasureResult(costs=(0.0033057994791666663,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.140754461288452, timestamp=1678321457.8515878) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8590461
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5015272
@@ -2219,9 +2080,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2332914
+ [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3307932
Finish loading 20 records
- Time cost of this operator: 0.001143
+ Time cost of this operator: 0.002310
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 f8b0e5c962..96e8c03148 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
@@ -360,10 +360,10 @@ 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 316.7 98.75 (1, 2, 10, 10, 3) 2 1 [316.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.04 0.948 (1, 6, 10, 10) 1 1 [3.04]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.302 (1, 1, 10, 10, 3) 1 1 [0.969]
- Total_time - 320.709 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.3 98.718 (1, 2, 10, 10, 3) 2 1 [317.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.135 0.975 (1, 6, 10, 10) 1 1 [3.135]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.987 0.307 (1, 1, 10, 10, 3) 1 1 [0.987]
+ Total_time - 321.422 - - - - -
@@ -428,10 +428,10 @@ 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 105.6 97.553 (1, 6, 10, 10, 1) 2 1 [105.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.658 (1, 6, 10, 10) 1 1 [1.795]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.854 0.789 (1, 3, 10, 10, 1) 1 1 [0.854]
- Total_time - 108.249 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.0 97.518 (1, 6, 10, 10, 1) 2 1 [103.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.781 1.686 (1, 6, 10, 10) 1 1 [1.781]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.795 (1, 3, 10, 10, 1) 1 1 [0.84]
+ Total_time - 105.621 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.220 seconds)
+ **Total running time of the script:** ( 1 minutes 26.555 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index d8ae836fa2..eb4a839b54 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 51.8MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 181MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.320 seconds)
+ **Total running time of the script:** ( 1 minutes 24.824 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 90f042ad47..c4ee74406f 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
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpxnt1lmd2/images/random'
+ '/tmp/tmpvvg03l7i/images/random'
@@ -309,7 +309,7 @@ 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], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpxnt1lmd2/images/target contains 8144 images
- /tmp/tmpxnt1lmd2/images/random contains 5000 images
+ /tmp/tmpvvg03l7i/images/target contains 8144 images
+ /tmp/tmpvvg03l7i/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 50s - loss: 0.2173 - accuracy: 0.9237 - val_loss: 0.1207 - val_accuracy: 0.9554 - 50s/epoch - 153ms/step
+ 328/328 - 48s - loss: 0.2087 - accuracy: 0.9258 - val_loss: 0.1165 - val_accuracy: 0.9596 - 48s/epoch - 148ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.1044 - accuracy: 0.9610 - val_loss: 0.1016 - val_accuracy: 0.9596 - 44s/epoch - 133ms/step
+ 328/328 - 45s - loss: 0.1042 - accuracy: 0.9584 - val_loss: 0.1054 - val_accuracy: 0.9600 - 45s/epoch - 137ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0710 - accuracy: 0.9743 - val_loss: 0.0954 - val_accuracy: 0.9656 - 43s/epoch - 132ms/step
+ 328/328 - 44s - loss: 0.0623 - accuracy: 0.9765 - val_loss: 0.1018 - val_accuracy: 0.9607 - 44s/epoch - 135ms/step
- <keras.callbacks.History object at 0x7fb57c591890>
+ <keras.callbacks.History object at 0x7fd06d52de90>
@@ -861,7 +861,7 @@ 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 46.662 seconds)
+ **Total running time of the script:** ( 4 minutes 35.263 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 b841e3eb45..f4bdc23392 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**07:48.333** total execution time for **how_to_work_with_microtvm** files:
+**07:45.411** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:46.662 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:35.263 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:23.220 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:26.555 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:20.320 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:24.824 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.441 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:11.065 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.690 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.705 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 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 6eb11df786..96ea292e3d 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
=================
-**00:47.316** total execution time for **how_to_work_with_relay** files:
+**00:50.158** 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``) | 00:34.076 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:37.651 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:11.320 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.597 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.914 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.903 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 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 762529f4dd..d89b3955c0 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
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fb4902c4830>
+ <function my_cuda_math_rule at 0x7fcf7e573710>
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 5624a603e1..426d687638 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
=================
-**00:08.797** total execution time for **how_to_work_with_schedules** files:
+**00:06.949** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.972 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.270 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.448 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.189 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.584 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.633 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.562 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.604 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.126 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.062 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.036 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 a8cfbdaf8c..f3fb2d759a 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
=================
-**00:32.222** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:33.724** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:32.215 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:33.717 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 791250b8f7..d9c0ca9e44 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ 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 34.35s!
+ resnet18_v1 inference graph built in 35.50s!
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 6faaedc205..3916b5b314 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ 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 23.34s!
+ yolov3-tiny inference graph built in 23.90s!
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 19a4bb4cf3..72de4a0f13 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:41.841** total execution time for **topic_vta_tutorials_frontend** files:
+**01:43.492** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.290 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:52.419 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.551 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.073 | 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 b3381e402d..0e7e2e0ad5 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
=================
-**00:03.167** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.194** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.697 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.706 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.470 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.488 | 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 57b2db4fbe..c6369f0e28 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
=================
-**00:00.788** total execution time for **topic_vta_tutorials** files:
+**00:00.819** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.413 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.421 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.375 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.397 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 8f5b05f0cb..d144e84d2b 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -318,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 96.648 ms
+ Execution time of this operator: 95.437 ms
@@ -434,7 +434,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.223 seconds)
+ **Total running time of the script:** ( 1 minutes 33.203 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 47c0e24cb1..e48070d8be 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 2.14/2.14 result: MeasureResult(costs=(0.12535433619999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2580337524414062, timestamp=1678319862.0638366) [('tile_y', [-1, 8]), ('tile_x', [-1, 2])],None,13
- No: 2 GFLOPS: 10.41/10.41 result: MeasureResult(costs=(0.025796567,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6771280765533447, timestamp=1678319862.737913) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
- No: 3 GFLOPS: 8.68/10.41 result: MeasureResult(costs=(0.030932515,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8485634326934814, timestamp=1678319864.7239118) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
- No: 4 GFLOPS: 10.06/10.41 result: MeasureResult(costs=(0.0266719474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7474157810211182, timestamp=1678319866.6362557) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
- No: 5 GFLOPS: 2.66/10.41 result: MeasureResult(costs=(0.10097175600000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8504841327667236, timestamp=1678319868.621185) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
- No: 6 GFLOPS: 11.51/11.51 result: MeasureResult(costs=(0.0233234726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6312999725341797, timestamp=1678319870.4712865) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
- No: 7 GFLOPS: 0.51/11.51 result: MeasureResult(costs=(0.5246637655999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.635518550872803, timestamp=1678319879.1259377) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
- No: 8 GFLOPS: 2.20/11.51 result: MeasureResult(costs=(0.12208912219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.199854850769043, timestamp=1678319881.3336918) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
- No: 9 GFLOPS: 10.36/11.51 result: MeasureResult(costs=(0.0259004844,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6367299556732178, timestamp=1678319882.0872421) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 10 GFLOPS: 10.65/11.51 result: MeasureResult(costs=(0.0251954118,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6173386573791504, timestamp=1678319882.749092) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+ No: 1 GFLOPS: 2.61/2.61 result: MeasureResult(costs=(0.1027501444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8946588039398193, timestamp=1678342380.7743597) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 2 GFLOPS: 1.24/2.61 result: MeasureResult(costs=(0.21638905519999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6978631019592285, timestamp=1678342384.4965248) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
+ No: 3 GFLOPS: 1.55/2.61 result: MeasureResult(costs=(0.1726559244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.001988410949707, timestamp=1678342388.821764) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 4 GFLOPS: 10.42/10.42 result: MeasureResult(costs=(0.0257712914,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6560153961181641, timestamp=1678342390.7604556) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+ No: 5 GFLOPS: 1.99/10.42 result: MeasureResult(costs=(0.1350411852,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.399169683456421, timestamp=1678342393.2936676) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+ No: 6 GFLOPS: 3.04/10.42 result: MeasureResult(costs=(0.0884382058,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6885795593261719, timestamp=1678342396.2553372) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+ No: 7 GFLOPS: 2.50/10.42 result: MeasureResult(costs=(0.107351902,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.952357530593872, timestamp=1678342398.2266138) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
+ No: 8 GFLOPS: 0.90/10.42 result: MeasureResult(costs=(0.299787507,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.028179407119751, timestamp=1678342403.2741692) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+ No: 9 GFLOPS: 10.45/10.45 result: MeasureResult(costs=(0.025699142200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6684181690216064, timestamp=1678342404.056666) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
+ No: 10 GFLOPS: 3.09/10.45 result: MeasureResult(costs=(0.08673808920000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6067490577697754, timestamp=1678342405.7035344) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index e6b52119ba..977c8d2d30 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 510.5504202200018, 'median': 510.6422028499992, 'std': 1.665563049841246}
+ {'mean': 520.8213620399988, 'median': 520.6977899499975, 'std': 2.7301109700505735}
@@ -545,30 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 8.52/ 17.46 GFLOPS | Progress: (4/20) | 12.11 s
[Task 1/25] Current/Best: 14.79/ 17.46 GFLOPS | Progress: (8/20) | 16.33 s
[Task 1/25] Current/Best: 22.82/ 23.61 GFLOPS | Progress: (12/20) | 18.59 s
[Task 1/25] Current/Best: 15.00/ 23.61 GFLOPS | Progress: (16/20) | 21.32 s
[Task 1/25] Current/Best: 19.14/ 23.61 GFLOPS | Progress: (20/20) | 23.48 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.60/ 16.77 GFLOPS | Progress: (4/20) | 5.05 s
[Task 2/25] Current/Best: 3.81/ 18.99 GFLOPS | Progress: (8/20) | 6.75 s
[Task 2/25] Current/Best: 16.13/ 18.99 GFLOPS | Progress: (12/20) | 9.62 s
[Task 2/25] Current/Best: 18.60/ 18.99 GFLOPS | Progress: (16/20) | 11.21 s
[Task 2/25] Current/Best: 5.67/ 22.68 GFLOPS | Progress: (20/20) | 12.57 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 11.84/ 23.16 GFLOPS | Progress: (4/20) | 4.75 s
[Task 3/25] Current/Best: 12.44/ 23.16 GFLOPS | Progress: (8/20) | 7.85 s
[Task 3/25] Current/Best: 9.87/ 23.16 GFLOPS | Progress: (12/20) | 10.41 s
[Task 3/25] Current/Best: 12.21/ 23.16 GFLOPS | Progress: (16/20) | 12.71 s
[Task 3/25] Current/Best: 14.24/ 23.16 GFLOPS | Progress: (20/20) | 15.67 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 16.79/ 21.27 GFLOPS | Progress: (4/20) | 4.83 s
[Task 4/25] Current/Best: 8.24/ 21.27 GFLOPS | Progress: (8/20) | 6.92 s
[Task 4/25] Current/Best: 21.28/ 21.28 GFLOPS | Progress: (12/20) | 15.03 s
[Task 4/25] Current/Best: 19.43/ 21.28 GFLOPS | Progress: (16/20) | 16.78 s
[Task 4/25] Current/Best: 6.40/ 21.28 GFLOPS | Progress: (20/20) | 21.27 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 6.95/ 22.75 GFLOPS | Progress: (4/20) | 4.69 s
[Task 5/25] Current/Best: 12.12/ 22.75 GFLOPS | Progress: (8/20) | 6.76 s
[Task 5/25] Current/Best: 13.20/ 22.75 GFLOPS | Progress: (12/20) | 8.89 s
[Task 5/25] Current/Best: 4.10/ 22.75 GFLOPS | Progress: (16/20) | 11.31 s
[Task 5/25] Current/Best: 11.03/ 22.75 GFLOPS | Progress: (20/20) | 14.03 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.64/ 17.76 GFLOPS | Progress: (4/20) | 6.57 s
[Task 6/25] Current/Best: 3.12/ 17.76 GFLOPS | Progress: (8/20) | 10.25 s
[Task 6/25] Current/Best: 14.16/ 17.76 GFLOPS | Progress: (12/20) | 12.46 s
[Task 6/25] Current/Best: 1.59/ 18.11 GFLOPS | Progress: (16/20) | 16.20 s
[Task 6/25] Current/Best: 10.90/ 18.11 GFLOPS | Progress: (20/20) | 19.16 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.62/ 12.27 GFLOPS | Progress: (4/20) | 5.89 s
[Task 7/25] Current/Best: 5.98/ 20.83 GFLOPS | Progress: (8/20) | 8.42 s
[Task 7/25] Current/Best: 15.88/ 21.31 GFLOPS | Progress: (12/20) | 10.90 s
[Task 7/25] Current/Best: 15.32/ 21.31 GFLOPS | Progress: (16/20) | 13.08 s
[Task 7/25] Current/Best: 11.67/ 21.31 GFLOPS | Progress: (20/20) | 15.84 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.23/ 12.82 GFLOPS | Progress: (4/20) | 7.77 s
[Task 8/25] Current/Best: 10.11/ 20.21 GFLOPS | Progress: (8/20) | 10.39 s
[Task 8/25] Current/Best: 13.06/ 20.21 GFLOPS | Progress: (12/20) | 22.17 s
[Task 8/25] Current/Best: 5.22/ 20.21 GFLOPS | Progress: (16/20) | 25.95 s
[Task 8/25] Current/Best: 5.64/ 20.21 GFLOPS | Progress: (20/20) | 28.96 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 6.22/ 15.43 GFLOPS | Progress: (4/20) | 4.85 s
[Task 9/25] Current/Best: 8.09/ 15.43 GFLOPS | Progress: (8/20) | 6.92 s
[Task 9/25] Current/Best: 12.67/ 16.41 GFLOPS | Progress: (12/20) | 8.65 s
[Task 9/25] Current/Best: 23.06/ 23.06 GFLOPS | Progress: (16/20) | 15.34 s
[Task 9/25] Current/Best: 12.10/ 23.06 GFLOPS | Progress: (20/20) | 22.84 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 15.09/ 15.90 GFLOPS | Progress: (4/20) | 5.25 s
[Task 10/25] Current/Best: 11.08/ 21.31 GFLOPS | Progress: (8/20) | 6.91 s
[Task 10/25] Current/Best: 16.13/ 21.31 GFLOPS | Progress: (12/20) | 8.97 s
[Task 10/25] Current/Best: 8.53/ 21.31 GFLOPS | Progress: (16/20) | 11.06 s
[Task 10/25] Current/Best: 11.32/ 21.31 GFLOPS | Progress: (20/20) | 13.28 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 15.42/ 18.15 GFLOPS | Progress: (4/20) | 5.41 s
[Task 11/25] Current/Best: 12.90/ 18.15 GFLOPS | Progress: (8/20) | 8.40 s
[Task 11/25] Current/Best: 23.74/ 23.74 GFLOPS | Progress: (12/20) | 10.57 s
[Task 11/25] Current/Best: 11.33/ 23.74 GFLOPS | Progress: (16/20) | 13.74 s
[Task 11/25] Current/Best: 19.39/ 23.74 GFLOPS | Progress: (20/20) | 16.24 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 17.06/ 21.06 GFLOPS | Progress: (4/20) | 4.57 s
[Task 12/25] Current/Best: 14.50/ 21.06 GFLOPS | Progress: (8/20) | 8.99 s
[Task 12/25] Current/Best: 13.60/ 21.06 GFLOPS | Progress: (12/20) | 11.73 s
[Task 12/25] Current/Best: 13.83/ 21.06 GFLOPS | Progress: (16/20) | 13.62 s
[Task 12/25] Current/Best: 18.38/ 21.06 GFLOPS | Progress: (20/20) | 16.04 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.40/ 19.80 GFLOPS | Progress: (4/20) | 5.74 s
[Task 13/25] Current/Best: 12.16/ 19.80 GFLOPS | Progress: (8/20) | 8.96 s
[Task 13/25] Current/Best: 19.35/ 19.80 GFLOPS | Progress: (12/20) | 11.90 s
[Task 13/25] Current/Best: 16.67/ 19.80 GFLOPS | Progress: (16/20) | 14.20 s
[Task 13/25] Current/Best: 15.55/ 19.80 GFLOPS | Progress: (20/20) | 16.96 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.45/ 12.53 GFLOPS | Progress: (4/20) | 7.39 s
[Task 14/25] Current/Best: 15.74/ 15.74 GFLOPS | Progress: (8/20) | 17.60 s
[Task 14/25] Current/Best: 9.44/ 15.74 GFLOPS | Progress: (12/20) | 20.34 s
[Task 14/25] Current/Best: 13.26/ 15.74 GFLOPS | Progress: (16/20) | 25.11 s
[Task 14/25] Current/Best: 11.23/ 15.74 GFLOPS | Progress: (20/20) | 30.60 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 5.81/ 18.23 GFLOPS | Progress: (4/20) | 11.68 s
[Task 15/25] Current/Best: 13.45/ 21.36 GFLOPS | Progress: (8/20) | 17.13 s
[Task 15/25] Current/Best: 18.29/ 21.36 GFLOPS | Progress: (12/20) | 23.29 s
[Task 15/25] Current/Best: 18.43/ 21.36 GFLOPS | Progress: (16/20) | 24.94 s
[Task 15/25] Current/Best: 13.84/ 21.36 GFLOPS | Progress: (20
/20) | 26.94 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 4.71/ 14.25 GFLOPS | Progress: (4/20) | 5.83 s
[Task 16/25] Current/Best: 10.71/ 15.31 GFLOPS | Progress: (8/20) | 8.09 s
[Task 16/25] Current/Best: 10.37/ 15.83 GFLOPS | Progress: (12/20) | 10.35 s
[Task 16/25] Current/Best: 12.15/ 19.14 GFLOPS | Progress: (16/20) | 14.05 s
[Task 16/25] Current/Best: 15.48/ 19.14 GFLOPS | Progress: (20/20) | 16.06 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.61/ 18.70 GFLOPS | Progress: (4/20) | 4.90 s
[Task 17/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (8/20) | 8.89 s
[Task 17/25] Current/Best: 18.97/ 19.31 GFLOPS | Progress: (12/20) | 11.60 s
[Task 17/25] Current/Best: 13.23/ 19.31 GFLOPS | Progress: (16/20) | 14.07 s
[Task 17/25] Current/Best: 6.40/ 19.31 GFLOPS | Progress: (20/20) | 17.76 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 6.01/ 15.02 GFLOPS | Progress: (4/20) | 6.76 s
[Task 18/25] Current/Best: 15.54/ 15.54 GFLOPS | Progress: (8/20) | 9.81 s
[Task 18/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 12.36 s
[Task 18/25] Current/Best: 5.78/ 19.05 GFLOPS | Progress: (16/20) | 14.84 s
[Task 18/25] Current/Best: 14.89/ 19.05 GFLOPS | Progress: (20/20) | 16.90 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.33/ 11.33 GFLOPS | Progress: (4/20) | 7.56 s
[Task 19/25] Current/Best: 7.37/ 11.33 GFLOPS | Progress: (8/20) | 13.93 s
[Task 19/25] Current/Best: 17.86/ 18.96 GFLOPS | Progress: (12/20) | 16.91 s
[Task 19/25] Current/Best: 9.26/ 18.96 GFLOPS | Progress: (16/20) | 22.04 s
[Task 19/25] Current/Best: 5.25/ 18.96 GFLOPS | Progress: (20/20) | 25.51 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.50/ 20.28 GFLOPS | Progress: (4/20) | 5.02 s
[Task 20/25] Current/Best: 9.72/ 20.28 GFLOPS | Progress: (8/20) | 8.04 s
[Task 20/25] Current/Best: 15.06/ 20.28 GFLOPS | Progress: (12/20) | 10.78 s
[Task 20/25] Current/Best: 10.10/ 21.64 GFLOPS | Progress: (16/20) | 15.57 s
[Task 20/25] Current/Best: 3.91/ 21.64 GFLOPS | Progress: (20/20) | 19.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 13.65/ 19.72 GFLOPS | Progress: (4/20) | 5.64 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 6.75/ 13.19 GFLOPS | Progress: (4/20) | 12.64 s
[Task 1/25] Current/Best: 14.20/ 22.00 GFLOPS | Progress: (8/20) | 15.30 s
[Task 1/25] Current/Best: 21.52/ 22.00 GFLOPS | Progress: (12/20) | 17.92 s
[Task 1/25] Current/Best: 15.07/ 22.00 GFLOPS | Progress: (16/20) | 20.15 s
[Task 1/25] Current/Best: 10.94/ 22.00 GFLOPS | Progress: (20/20) | 26.46 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 4.44 s
[Task 2/25] Current/Best: 11.35/ 19.91 GFLOPS | Progress: (8/20) | 6.43 s
[Task 2/25] Current/Best: 6.46/ 19.91 GFLOPS | Progress: (12/20) | 7.84 s
[Task 2/25] Current/Best: 8.74/ 22.41 GFLOPS | Progress: (16/20) | 9.69 s
[Task 2/25] Current/Best: 11.84/ 22.41 GFLOPS | Progress: (20/20) | 11.06 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 13.04/ 13.04 GFLOPS | Progress: (4/20) | 5.54 s
[Task 3/25] Current/Best: 8.51/ 19.16 GFLOPS | Progress: (8/20) | 7.91 s
[Task 3/25] Current/Best: 17.88/ 19.16 GFLOPS | Progress: (12/20) | 10.37 s
[Task 3/25] Current/Best: 5.08/ 19.90 GFLOPS | Progress: (16/20) | 12.79 s
[Task 3/25] Current/Best: 16.89/ 19.90 GFLOPS | Progress: (20/20) | 15.11 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 10.99/ 12.60 GFLOPS | Progress: (4/20) | 6.96 s
[Task 4/25] Current/Best: 15.89/ 17.21 GFLOPS | Progress: (8/20) | 9.60 s
[Task 4/25] Current/Best: 7.94/ 17.21 GFLOPS | Progress: (12/20) | 11.58 s
[Task 4/25] Current/Best: 13.48/ 17.21 GFLOPS | Progress: (16/20) | 13.75 s
[Task 4/25] Current/Best: 7.08/ 17.21 GFLOPS | Progress: (20/20) | 17.49 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.85/ 18.78 GFLOPS | Progress: (4/20) | 5.08 s
[Task 5/25] Current/Best: 17.82/ 18.78 GFLOPS | Progress: (8/20) | 6.94 s
[Task 5/25] Current/Best: 16.25/ 18.78 GFLOPS | Progress: (12/20) | 8.75 s
[Task 5/25] Current/Best: 11.73/ 18.78 GFLOPS | Progress: (16/20) | 11.42 s
[Task 5/25] Current/Best: 10.82/ 18.78 GFLOPS | Progress: (20/20) | 13.98 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 4.59/ 17.80 GFLOPS | Progress: (4/20) | 6.26 s
[Task 6/25] Current/Best: 16.96/ 17.80 GFLOPS | Progress: (8/20) | 8.78 s
[Task 6/25] Current/Best: 9.13/ 17.90 GFLOPS | Progress: (12/20) | 11.65 s
[Task 6/25] Current/Best: 3.89/ 17.90 GFLOPS | Progress: (16/20) | 15.12 s
[Task 6/25] Current/Best: 8.43/ 18.20 GFLOPS | Progress: (20/20) | 18.11 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.30/ 16.86 GFLOPS | Progress: (4/20) | 5.49 s
[Task 7/25] Current/Best: 15.93/ 20.63 GFLOPS | Progress: (8/20) | 7.70 s
[Task 7/25] Current/Best: 9.38/ 20.63 GFLOPS | Progress: (12/20) | 11.05 s
[Task 7/25] Current/Best: 19.00/ 20.63 GFLOPS | Progress: (16/20) | 13.15 s
[Task 7/25] Current/Best: 16.20/ 20.63 GFLOPS | Progress: (20/20) | 15.58 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 18.39/ 18.39 GFLOPS | Progress: (4/20) | 5.71 s
[Task 8/25] Current/Best: 8.85/ 21.31 GFLOPS | Progress: (8/20) | 9.25 s
[Task 8/25] Current/Best: 20.59/ 21.31 GFLOPS | Progress: (12/20) | 11.48 s
[Task 8/25] Current/Best: 7.69/ 21.31 GFLOPS | Progress: (16/20) | 18.06 s
[Task 8/25] Current/Best: 15.10/ 21.31 GFLOPS | Progress: (20/20) | 29.45 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 18.90/ 23.69 GFLOPS | Progress: (4/20) | 6.54 s
[Task 9/25] Current/Best: 11.59/ 23.69 GFLOPS | Progress: (8/20) | 9.35 s
[Task 9/25] Current/Best: 8.21/ 23.69 GFLOPS | Progress: (12/20) | 13.14 s
[Task 9/25] Current/Best: 10.34/ 23.69 GFLOPS | Progress: (16/20) | 21.33 s
[Task 9/25] Current/Best: 12.29/ 23.69 GFLOPS | Progress: (20/20
) | 23.36 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 21.57/ 21.57 GFLOPS | Progress: (4/20) | 4.55 s
[Task 10/25] Current/Best: 13.14/ 21.57 GFLOPS | Progress: (8/20) | 6.34 s Done.
+
[Task 10/25] Current/Best: 11.96/ 21.57 GFLOPS | Progress: (12/20) | 8.84 s
[Task 10/25] Current/Best: 11.08/ 21.57 GFLOPS | Progress: (16/20) | 11.09 s
[Task 10/25] Current/Best: 9.28/ 21.57 GFLOPS | Progress: (20/20) | 13.18 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 6.18/ 11.82 GFLOPS | Progress: (4/20) | 6.39 s
[Task 11/25] Current/Best: 11.81/ 19.06 GFLOPS | Progress: (8/20) | 9.93 s
[Task 11/25] Current/Best: 12.09/ 19.06 GFLOPS | Progress: (12/20) | 12.51 s
[Task 11/25] Current/Best: 18.12/ 19.06 GFLOPS | Progress: (16/20) | 14.96 s
[Task 11/25] Current/Best: 13.25/ 19.06 GFLOPS | Progress: (20/20) | 17.78 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.63/ 13.07 GFLOPS | Progress: (4/20) | 8.80 s
[Task 12/25] Current/Best: 1.60/ 22.05 GFLOPS | Progress: (8/20) | 12.55 s
[Task 12/25] Current/Best: 17.58/ 22.05 GFLOPS | Progress: (12/20) | 14.81 s
[Task 12/25] Current/Best: 9.35/ 22.05 GFLOPS | Progress: (16/20) | 17.55 s
[Task 12/25] Current/Best: 13.02/ 22.05 GFLOPS | Progress: (20/20) | 20.86 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 18.44/ 19.38 GFLOPS | Progress: (4/20) | 5.60 s
[Task 13/25] Current/Best: 18.18/ 19.38 GFLOPS | Progress: (8/20) | 9.25 s
[Task 13/25] Current/Best: 17.77/ 19.68 GFLOPS | Progress: (12/20) | 11.22 s
[Task 13/25] Current/Best: 13.99/ 19.68 GFLOPS | Progress: (16/20) | 13.33 s
[Task 13/25] Current/Best: 9.03/ 19.68 GFLOPS | Progress: (20/20) | 16.74 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 2.90/ 17.66 GFLOPS | Progress: (4/20) | 5.41 s
[Task 14/25] Current/Best: 14.11/ 17.66 GFLOPS | Progress: (8/20) | 10.33 s
[Task 14/25] Current/Best: 14.89/ 17.66 GFLOPS | Progress: (12/20) | 12.62 s
[Task 14/25] Current/Best: 12.41/ 17.66 GFLOPS | Progress: (16/20) | 15.54 s
[Task 14/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (20/20) | 19.32 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.93/ 13.93 GFLOPS | Progress: (4/20) | 4.83 s
[Task 15/25] Current/Best: 6.49/ 19.87 GFLOPS | Progress: (8/20) | 7.75 s
[Task 15/25] Current/Best: 18.10/ 19.87 GFLOPS | Progress: (12/20) | 9.98 s
[Task 15/25] Current/Best: 15.75/ 19.87 GFLOPS | Progress: (16/20) | 14.95 s
[Task 15/25] Current/Best: 9.55/ 19.87 GFLOPS | Progress: (20/20) | 21.15 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.85/ 12.50 GFLOPS | Progress: (4/20) | 6.70 s
[Task 16/25] Current/Best: 6.11/ 20.86 GFLOPS | Progress: (8/20) | 8.63 s
[Task 16/25] Current/Best: 9.79/ 20.86 GFLOPS | Progress: (12/20) | 12.63 s
[Task 16/25] Current/Best: 15.31/ 20.86 GFLOPS | Progress: (16/20) | 15.37 s
[Task 16/25] Current/Best: 11.80/ 20.86 GFLOPS | Progress: (20/20)
| 18.14 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.90/ 16.82 GFLOPS | Progress: (4/20) | 7.58 s
[Task 17/25] Current/Best: 11.41/ 20.44 GFLOPS | Progress: (8/20) | 10.19 s
[Task 17/25] Current/Best: 15.99/ 22.29 GFLOPS | Progress: (12/20) | 13.30 s
[Task 17/25] Current/Best: 12.20/ 22.29 GFLOPS | Progress: (16/20) | 15.70 s
[Task 17/25] Current/Best: 9.46/ 22.29 GFLOPS | Progress: (20/20) | 18.05 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 4.53/ 15.30 GFLOPS | Progress: (4/20) | 6.02 s
[Task 18/25] Current/Best: 8.25/ 19.40 GFLOPS | Progress: (8/20) | 9.09 s
[Task 18/25] Current/Best: 17.69/ 19.40 GFLOPS | Progress: (12/20) | 10.95 s
[Task 18/25] Current/Best: 6.29/ 19.40 GFLOPS | Progress: (16/20) | 13.07 s
[Task 18/25] Current/Best: 18.02/ 19.40 GFLOPS | Progress: (20/20) | 15.89 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 13.14/ 22.73 GFLOPS | Progress: (4/20) | 6.60 s
[Task 19/25] Current/Best: 20.98/ 22.73 GFLOPS | Progress: (8/20) | 9.07 s
[Task 19/25] Current/Best: 12.39/ 22.73 GFLOPS | Progress: (12/20) | 11.81 s
[Task 19/25] Current/Best: 22.27/ 22.73 GFLOPS | Progress: (16/20) | 15.41 s
[Task 19/25] Current/Best: 19.43/ 22.73 GFLOPS | Progress: (20/20) | 18.24 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.69/ 14.40 GFLOPS | Progress: (4/20) | 5.12 s
[Task 20/25] Current/Best: 16.75/ 16.75 GFLOPS | Progress: (8/20) | 7.59 s
[Task 20/25] Current/Best: 14.98/ 16.75 GFLOPS | Progress: (12/20) | 10.89 s Done.
+
[Task 20/25] Current/Best: 10.48/ 16.75 GFLOPS | Progress: (16/20) | 17.69 s
[Task 20/25] Current/Best: 17.67/ 17.67 GFLOPS | Progress: (20/20) | 19.86 s Done.
+
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 5.25/ 17.42 GFLOPS | Progress: (4/20) | 4.82 s
[Task 21/25] Current/Best: 19.63/ 19.63 GFLOPS | Progress: (8/20) | 7.81 s
[Task 21/25] Current/Best: 11.72/ 22.38 GFLOPS | Progress: (12/20) | 10.43 s
[Task 21/25] Current/Best: 2.53/ 22.38 GFLOPS | Progress: (16/20) | 13.66 s
[Task 21/25] Current/Best: 10.70/ 22.53 GFLOPS | Progress: (20/20) | 16.23 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 16.30/ 17.97 GFLOPS | Progress: (4/20) | 5.68 s
[Task 22/25] Current/Best: 8.94/ 17.97 GFLOPS | Progress: (8/20) | 10.20 s
[Task 22/25] Current/Best: 5.35/ 17.97 GFLOPS | Progress: (12/20) | 12.25 s
[Task 22/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (16/20) | 14.49 s
[Task 22/25] Current/Best: 18.41/ 20.61 GFLOPS | Progress: (20/2
0) | 17.02 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (4/20) | 5.64 s
[Task 23/25] Current/Best: 6.00/ 20.08 GFLOPS | Progress: (8/20) | 10.13 s
[Task 23/25] Current/Best: 7.67/ 20.08 GFLOPS | Progress: (12/20) | 13.50 s
[Task 23/25] Current/Best: 18.73/ 20.08 GFLOPS | Progress: (16/20) | 17.37 s
[Task 23/25] Current/Best: 8.13/ 20.08 GFLOPS | Progress: (20/20) | 21.63 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.27/ 8.04 GFLOPS | Progress: (4/20) | 13.75 s
[Task 24/25] Current/Best: 1.55/ 8.04 GFLOPS | Progress: (8/20) | 26.16 s
[Task 24/25] Current/Best: 3.95/ 9.04 GFLOPS | Progress: (12/20) | 29.39 s
[Task 24/25] Current/Best: 3.59/ 9.04 GFLOPS | Progress: (16/20) | 34.55 s
[Task 24/25] Current/Best: 8.19/ 9.76 GFLOPS | Progress: (20/20) | 45.21 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
- Done.
-
[Task 21/25] Current/Best: 16.15/ 19.72 GFLOPS | Progress: (8/20) | 7.90 s
[Task 21/25] Current/Best: 14.13/ 19.72 GFLOPS | Progress: (12/20) | 11.64 s
[Task 21/25] Current/Best: 9.07/ 21.47 GFLOPS | Progress: (16/20) | 14.21 s
[Task 21/25] Current/Best: 15.80/ 21.47 GFLOPS | Progress: (20/20) | 17.77 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 12.57/ 12.57 GFLOPS | Progress: (4/20) | 4.66 s
[Task 22/25] Current/Best: 12.06/ 16.77 GFLOPS | Progress: (8/20) | 6.85 s
[Task 22/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (12/20) | 9.91 s
[Task 22/25] Current/Best: 10.86/ 20.92 GFLOPS | Progress: (16/20) | 11.54 s
[Task 22/25] Current/Best: 15.74/ 20.92 GFLOPS | Progress: (20/20) | 13.22 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 19.06/ 20.00 GFLOPS | Progress: (4/20) | 5.37 s
[Task 23/25] Current/Best: 10.19/ 20.12 GFLOPS | Progress: (8/20) | 8.79 s
[Task 23/25] Current/Best: 11.95/ 20.12 GFLOPS | Progress: (12/20) | 12.83 s
[Task 23/25] Current/Best: 3.08/ 20.12 GFLOPS | Progress: (16/20) | 17.08 s
[Task 23/25] Current/Best: 14.05/ 20.12 GFLOPS | Progress: (20/20) | 19.74 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.40/ 6.40 GFLOPS | Progress: (4/20) | 13.72 s
[Task 24/25] Current/Best: 3.57/ 9.87 GFLOPS | Progress: (8/20) | 17.05 s
[Task 24/25] Current/Best: 2.31/ 9.87 GFLOPS | Progress: (12/20) | 28.01 s
[Task 24/25] Current/Best: 3.70/ 10.70 GFLOPS | Progress: (16/20) | 40.30 s
[Task 24/25] Current/Best: 3.34/ 10.70 GFLOPS | Progress: (20/20) | 46.43 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 1.55/ 6.95 GFLOPS | Progress: (4/20) | 5.26 s
[Task 25/25] Current/Best: 8.52/ 9.34 GFLOPS | Progress: (8/20) | 10.29 s
[Task 25/25] Current/Best: 8.82/ 9.34 GFLOPS | Progress: (12/20) | 11.64 s
[Task 25/25] Current/Best: 5.95/ 9.34 GFLOPS | Progress: (16/20) | 13.08 s
[Task 25/25] Current/Best: 4.61/ 9.34 GFLOPS | Progress: (20/20) | 24.03 s
+
[Task 25/25] Current/Best: 2.86/ 9.03 GFLOPS | Progress: (4/20) | 13.73 s
[Task 25/25] Current/Best: 5.86/ 9.03 GFLOPS | Progress: (8/20) | 17.97 s
[Task 25/25] Current/Best: 7.29/ 9.03 GFLOPS | Progress: (12/20) | 22.94 s
[Task 25/25] Current/Best: 1.55/ 9.03 GFLOPS | Progress: (16/20) | 33.90 s
[Task 25/25] Current/Best: 5.56/ 9.03 GFLOPS | Progress: (20/20) | 36.86 s
@@ -664,9 +665,9 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
- class='n02123159 tiger cat' with probability=0.356379
- class='n02124075 Egyptian cat' with probability=0.019712
+ class='n02123045 tabby, tabby cat' with probability=0.621105
+ class='n02123159 tiger cat' with probability=0.356377
+ class='n02124075 Egyptian cat' with probability=0.019713
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -722,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.13500321999845, 'median': 415.84399574999225, 'std': 3.0956879571744502}
- unoptimized: {'mean': 510.5504202200018, 'median': 510.6422028499992, 'std': 1.665563049841246}
+ optimized: {'mean': 432.349127399998, 'median': 433.6005759499926, 'std': 5.591029240686418}
+ unoptimized: {'mean': 520.8213620399988, 'median': 520.6977899499975, 'std': 2.7301109700505735}
@@ -746,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 21.345 seconds)
+ **Total running time of the script:** ( 12 minutes 19.074 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 6f473c3f23..9eca64277a 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.259e-07 secs/op
+ 1.271e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 3530279c74..f91b5d65ce 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x21801380)), stage(b, placeholder(b, 0x23dd0ef0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T [...]
+ [stage(a, placeholder(a, 0xa81c8a0)), stage(b, placeholder(b, 0x2214beb0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 9f914d7df0..9164134d7a 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**15:43.002** total execution time for **tutorial** files:
+**16:06.908** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:21.345 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:19.074 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:13.223 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:33.203 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.149 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.652 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.243 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.954 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:29.416 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:33.433 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.619 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.535 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.844 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.872 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.162 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.186 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 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 a3eaa18da0..6e4f814f22 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -286,7 +286,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000007
- naive: 0.000009
+ naive: 0.000007
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000031
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.8646999989141475e-06 1.0
- naive 9.327e-06 1.3586901104892184
- parallel 6.9454000000000005e-06 1.0117557942952522
- vector 2.4621e-05 3.5866097577307863
+ numpy 7.299419999071688e-06 1.0
+ naive 6.783699999999999e-06 0.9293478113141488
+ parallel 6.9638e-06 0.9540210045298981
+ vector 3.0512899999999997e-05 4.18018143960486
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017811
+ Numpy running time: 0.018837
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.355344
+ none: 3.453174
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.292092
+ blocking: 0.295932
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.347297
+ vectorization: 0.336475
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116573
+ loop permutation: 0.119338
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109130
+ array packing: 0.110082
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.109929
+ block caching: 0.111686
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146105
+ parallelization: 0.146865
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3553441144 1.0
- blocking 0.2920919691 0.08705276095123606
- vectorization 0.34729719340000004 0.10350568572371406
- loop permutation 0.1165725155 0.03474234281953683
- array packing 0.10912982280000001 0.03252418204489125
- block caching 0.10992877109999999 0.03276229422437566
- parallelization 0.14610499329999999 0.04354396697285589
+ none 3.4531739437999995 1.0
+ blocking 0.2959322071 0.0856986100081438
+ vectorization 0.33647518449999997 0.09743939632815898
+ loop permutation 0.1193382231 0.034558995591364806
+ array packing 0.1100816614 0.031878400333017136
+ block caching 0.1116864689 0.03234313437946775
+ parallelization 0.14686541130000003 0.0425305570151453
@@ -1596,7 +1596,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.149 seconds)
+ **Total running time of the script:** ( 1 minutes 1.652 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 46637a169c..9e80c70ef3 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-1453fe07807088c248dfd1ed5cc4785d5a07fd3b
+6b4e3d08ea0155dad5a04272e196b18b3725150b
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 4aa2d20e9a..d4e52d44bc 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -590,7 +590,7 @@ 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 20.209 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.704 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 9335097c3b..cf944889b1 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -511,7 +511,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<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 965ms/step
+1/1 [==============================] - 1s 1s/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 9d9755781b..b9eb776276 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -444,7 +444,7 @@
<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.zip13064ef0-01fe-40c0-8830-31cc39add181 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.zipd677e57f-ec27-4d38-b579-f935463c05f8 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 c08d7f4cee..10e673ccad 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,14 +454,13 @@ 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]
- 6%|6 | 2.66M/41.5M [00:00<00:02, 19.7MB/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:01, 30.9MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 39.0MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 42.9MB/s]
- 64%|######3 | 26.4M/41.5M [00:00<00:00, 41.1MB/s]
- 82%|########2 | 34.1M/41.5M [00:01<00:00, 33.2MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 34.0MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 36.8MB/s]
+ 17%|#6 | 6.89M/41.5M [00:00<00:00, 72.2MB/s]
+ 33%|###3 | 13.8M/41.5M [00:00<00:00, 61.1MB/s]
+ 48%|####7 | 19.7M/41.5M [00:00<00:00, 36.9MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 38.8MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 48.1MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 42.3MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 44.9MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index e70f08c91e..3b0b5e9d3a 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,10 +437,12 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
- 55%|#####4 | 24.4M/44.7M [00:00<00:00, 72.0MB/s]
- 99%|#########8| 44.0M/44.7M [00:00<00:00, 115MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 93.3MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 54.9MB/s]
+ 36%|###6 | 16.1M/44.7M [00:00<00:00, 69.3MB/s]
+ 54%|#####3 | 24.1M/44.7M [00:00<00:00, 75.3MB/s]
+ 76%|#######6 | 34.1M/44.7M [00:00<00:00, 78.6MB/s]
+ 93%|#########3| 41.7M/44.7M [00:00<00:00, 76.2MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 77.7MB/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 1f6cdd4418..d0c7bbd9cc 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -654,7 +654,7 @@ 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 25.418 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.975 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 162605400b..6952a0dd64 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>06:42.715</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:57.081</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,43 +354,43 @@
</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>01:25.418</p></td>
+<td><p>01:26.975</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>01:20.209</p></td>
+<td><p>01:22.704</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>00:55.879</p></td>
+<td><p>00:59.988</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>00:38.679</p></td>
+<td><p>00:40.374</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:32.081</p></td>
+<td><p>00:33.401</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="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>00:30.934</p></td>
+<td><p>00:31.895</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>00:27.667</p></td>
+<td><p>00:27.824</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>00:26.213</p></td>
+<td><p>00:27.111</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>00:22.937</p></td>
+<td><p>00:24.022</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>00:02.697</p></td>
+<td><p>00:02.788</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 43b746db79..86f357292b 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -925,7 +925,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2679.2213 2677.6973 2684.0391 2676.3311 2.7731
+ 2680.9920 2680.4620 2684.3987 2679.0878 1.7751
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
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 74c37e93df..50fa330fe6 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -667,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7123 15.6223 16.2050 15.5184 0.2118
+ 16.3294 16.3073 16.5066 16.1819 0.1016
</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 63afb3ef69..2f4834d030 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,26 +459,27 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 4%|4 | 6.83M/170M [00:00<00:02, 71.6MB/s]
- 9%|9 | 16.0M/170M [00:00<00:02, 67.4MB/s]
- 13%|#3 | 22.5M/170M [00:00<00:02, 63.5MB/s]
- 17%|#6 | 28.5M/170M [00:00<00:02, 52.9MB/s]
- 22%|##2 | 37.7M/170M [00:00<00:02, 65.5MB/s]
- 28%|##7 | 47.4M/170M [00:00<00:01, 76.3MB/s]
- 32%|###2 | 55.1M/170M [00:00<00:01, 74.8MB/s]
- 38%|###7 | 64.0M/170M [00:00<00:01, 71.9MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 70.8MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 71.8MB/s]
- 52%|#####1 | 87.7M/170M [00:01<00:01, 74.2MB/s]
- 57%|#####6 | 96.0M/170M [00:01<00:01, 73.0MB/s]
- 61%|######1 | 104M/170M [00:01<00:01, 63.3MB/s]
- 66%|######6 | 113M/170M [00:01<00:00, 70.7MB/s]
- 74%|#######3 | 125M/170M [00:01<00:00, 85.6MB/s]
- 79%|#######8 | 134M/170M [00:01<00:00, 86.3MB/s]
- 84%|########3 | 142M/170M [00:02<00:00, 82.1MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 79.2MB/s]
- 95%|#########4| 161M/170M [00:02<00:00, 82.5MB/s]
-100%|##########| 170M/170M [00:02<00:00, 75.8MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 64.3MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 54.9MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:02, 59.2MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:02, 54.2MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:02, 61.9MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:01, 67.2MB/s]
+ 33%|###2 | 56.0M/170M [00:00<00:01, 71.5MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:01, 68.3MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 66.6MB/s]
+ 48%|####8 | 81.7M/170M [00:01<00:01, 75.8MB/s]
+ 53%|#####2 | 89.2M/170M [00:01<00:01, 76.4MB/s]
+ 57%|#####6 | 96.7M/170M [00:01<00:01, 57.5MB/s]
+ 63%|######2 | 106M/170M [00:01<00:00, 67.2MB/s]
+ 67%|######7 | 114M/170M [00:01<00:00, 71.6MB/s]
+ 72%|#######1 | 122M/170M [00:01<00:00, 70.3MB/s]
+ 76%|#######6 | 129M/170M [00:02<00:00, 72.1MB/s]
+ 81%|########1 | 138M/170M [00:02<00:00, 74.4MB/s]
+ 88%|########8 | 150M/170M [00:02<00:00, 87.3MB/s]
+ 93%|#########3| 158M/170M [00:02<00:00, 61.2MB/s]
+ 97%|#########7| 165M/170M [00:02<00:00, 57.4MB/s]
+100%|##########| 170M/170M [00:02<00:00, 65.5MB/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=& [...]
@@ -576,7 +577,7 @@ 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 29.941 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 57.575 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 106705370b..118752d4e8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,8 +500,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 74.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 78.2MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 35.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 49.8MB/s]
</pre></div>
</div>
</div>
@@ -592,7 +592,7 @@ 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)
- 90.1262 90.1053 90.8286 89.7640 0.2328
+ 90.3788 90.2946 92.4767 90.1564 0.3383
</pre></div>
</div>
<div class="admonition note">
@@ -631,7 +631,7 @@ 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 16.605 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.495 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 92c49dc1ef..af4acf818c 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -585,7 +585,7 @@ 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)
- 119.3569 119.4587 120.4381 115.8352 0.7321
+ 122.3517 122.2107 127.3617 121.4043 0.7275
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ 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 28.628 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 36.166 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 0cca01e270..671346c1a4 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -526,7 +526,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 39.698 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.525 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 c9506d9ba1..617366e288 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,25 +468,22 @@ 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]
- 1%| | 1129/132723 [00:00<00:11, 11160.32KB/s]
- 3%|2 | 3478/132723 [00:00<00:07, 18377.73KB/s]
- 6%|5 | 7417/132723 [00:00<00:04, 27902.28KB/s]
- 11%|# | 14009/132723 [00:00<00:02, 42868.67KB/s]
- 17%|#7 | 22679/132723 [00:00<00:01, 58646.85KB/s]
- 24%|##3 | 31423/132723 [00:00<00:01, 68423.43KB/s]
- 30%|### | 40148/132723 [00:00<00:01, 74571.75KB/s]
- 37%|###6 | 48912/132723 [00:00<00:01, 78727.23KB/s]
- 43%|####3 | 57649/132723 [00:00<00:00, 81424.64KB/s]
- 50%|####9 | 65794/132723 [00:01<00:00, 75145.68KB/s]
- 56%|#####6 | 74576/132723 [00:01<00:00, 78809.10KB/s]
- 62%|######2 | 82544/132723 [00:01<00:00, 62226.50KB/s]
- 69%|######8 | 91278/132723 [00:01<00:00, 68437.78KB/s]
- 74%|#######4 | 98666/132723 [00:01<00:00, 65354.91KB/s]
- 81%|######## | 107375/132723 [00:01<00:00, 70975.71KB/s]
- 87%|########6 | 114836/132723 [00:01<00:00, 62718.45KB/s]
- 93%|#########3| 123563/132723 [00:01<00:00, 68891.99KB/s]
-100%|#########9| 132419/132723 [00:02<00:00, 74088.62KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 66094.37KB/s]
+ 5%|5 | 6667/132723 [00:00<00:01, 66660.21KB/s]
+ 11%|#1 | 15213/132723 [00:00<00:01, 77709.57KB/s]
+ 17%|#7 | 23089/132723 [00:00<00:01, 78184.78KB/s]
+ 24%|##3 | 31735/132723 [00:00<00:01, 81449.95KB/s]
+ 30%|### | 40354/132723 [00:00<00:01, 83155.44KB/s]
+ 37%|###6 | 49007/132723 [00:00<00:00, 84300.13KB/s]
+ 43%|####3 | 57691/132723 [00:00<00:00, 85119.50KB/s]
+ 50%|##### | 66442/132723 [00:00<00:00, 85877.05KB/s]
+ 57%|#####6 | 75161/132723 [00:00<00:00, 86286.32KB/s]
+ 63%|######3 | 83790/132723 [00:01<00:00, 85666.83KB/s]
+ 70%|######9 | 92493/132723 [00:01<00:00, 86079.31KB/s]
+ 76%|#######6 | 101232/132723 [00:01<00:00, 86474.02KB/s]
+ 83%|########2 | 109915/132723 [00:01<00:00, 86574.76KB/s]
+ 89%|########9 | 118630/132723 [00:01<00:00, 86746.35KB/s]
+ 96%|#########5| 127307/132723 [00:01<00:00, 86744.53KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 84701.86KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -525,7 +522,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 49.677 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 58.707 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 fc6098b47f..22ce016c5d 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>15:19.269</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>16:19.020</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -354,39 +354,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:49.677</p></td>
+<td><p>03:58.707</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>03:29.941</p></td>
+<td><p>03:57.575</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>02:28.628</p></td>
+<td><p>02:36.166</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:39.698</p></td>
+<td><p>01:43.525</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>01:16.605</p></td>
+<td><p>01:21.495</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:56.267</p></td>
+<td><p>00:58.395</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:42.796</p></td>
+<td><p>00:45.109</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:28.051</p></td>
+<td><p>00:29.140</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:27.601</p></td>
+<td><p>00:28.901</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 498a30a0c0..713fd3d07e 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -624,7 +624,7 @@ 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.zip914073f8-611c-444e-aff3-34937d89d68b 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.zip94ac835c-f995-4cb0-b2f7-877771d9ffcf 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 b0dcf64c8d..790145e4c2 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:55.751</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:58.857</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,19 +354,19 @@
</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>00:51.808</p></td>
+<td><p>00:54.633</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>00:02.819</p></td>
+<td><p>00:03.023</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>00:01.115</p></td>
+<td><p>00:01.191</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>00:00.009</p></td>
+<td><p>00:00.010</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 78361a69f6..f90407656d 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -531,10 +531,10 @@ 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: 22758us [22758us] (49.17%; 49.17%)
-FoldScaleAxis: 23528us [9us] (50.83%; 50.83%)
- FoldConstant: 23519us [1800us] (50.81%; 99.96%)
- InferType: 21719us [21719us] (46.92%; 92.35%)
+InferType: 23430us [23430us] (48.59%; 48.59%)
+FoldScaleAxis: 24786us [10us] (51.41%; 51.41%)
+ FoldConstant: 24776us [1908us] (51.39%; 99.96%)
+ InferType: 22868us [22868us] (47.43%; 92.30%)
</pre></div>
</div>
</div>
@@ -556,10 +556,10 @@ 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: 21886us [21886us] (48.37%; 48.37%)
-FoldScaleAxis: 23357us [6us] (51.63%; 51.63%)
- FoldConstant: 23351us [1734us] (51.61%; 99.97%)
- InferType: 21617us [21617us] (47.78%; 92.58%)
+InferType: 23996us [23996us] (49.21%; 49.21%)
+FoldScaleAxis: 24771us [10us] (50.79%; 50.79%)
+ FoldConstant: 24761us [1957us] (50.77%; 99.96%)
+ InferType: 22804us [22804us] (46.76%; 92.10%)
</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 c3eec4b08c..f459537255 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -580,7 +580,7 @@ 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: 49.179840 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 51.304000 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 b6a98435e2..64ff38c902 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ 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: 9.528096 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.327136 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 26139919b0..ea9f12d776 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -477,8 +477,8 @@ 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: 0.018623
-Baseline: 3.480098
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019816
+Baseline: 3.548278
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -537,7 +537,7 @@ 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: 0.312424
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.341101
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ 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: 0.341044
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.362876
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -649,7 +649,7 @@ 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: 0.116375
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.134954
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -726,7 +726,7 @@ 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: 0.108872
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111578
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -804,7 +804,7 @@ 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: 0.111690
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112967
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -884,7 +884,7 @@ class Module:
<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: 0.147042
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.149115
</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 4cfea54c01..848e3ce903 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.456</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:36.800</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</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>00:32.674</p></td>
+<td><p>00:34.133</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>00:01.612</p></td>
+<td><p>00:01.574</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>00:01.170</p></td>
+<td><p>00:01.093</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index 54c61edc3c..5e2e61b0f0 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>09:54.087</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:13.968</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -354,27 +354,27 @@
</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>06:02.332</p></td>
+<td><p>06:14.515</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>01:42.569</p></td>
+<td><p>01:47.121</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>01:08.047</p></td>
+<td><p>01:09.481</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>00:32.574</p></td>
+<td><p>00:33.824</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>00:14.473</p></td>
+<td><p>00:14.704</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>00:14.092</p></td>
+<td><p>00:14.323</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 9929d7f046..7020d68e1a 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
@@ -511,11 +511,11 @@ class Module:
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.launch_thread("blockIdx.x", 16)
- conv2d_nchw = T.allocate([7], "float32", "local")
- pad_temp_shared = T.allocate([2592], "float32", "shared")
- kernel_shared = T.allocate([9216], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 224)
- conv2d_nchw_1 = T.Buffer((1,), data=conv2d_nchw, scope="local", align=4)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([324], "float32", "shared")
+ kernel_shared = T.allocate([1152], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 112)
+ conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
@@ -523,453 +523,124 @@ class Module:
conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
- for rc_outer_outer in range(16):
- cse_var_2: T.int32 = rc_outer_outer * 1568
- cse_var_1: T.int32 = rc_outer_outer * 288
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer in range(128):
+ cse_var_2: T.int32 = rc_outer_outer * 196
+ cse_var_1: T.int32 = rc_outer_outer * 36
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((2592,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((324,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 224):
+ with T.launch_thread(threadIdx_x_1, 112):
pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(9 <= (threadIdx_x_1 + 43) % 81 and (threadIdx_x_1 + 43) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 81 * 49 + (threadIdx_x_1 + 43) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 672] = T.if_then_else(9 <= (threadIdx_x_1 + 24) % 81 and (threadIdx_x_1 + 24) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 672) // 81 * 49 + (threadIdx_x_1 + 24) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 896] = T.if_then_else(9 <= (threadIdx_x_1 + 5) % 81 and (threadIdx_x_1 + 5) % 81 < 72 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 896) // 81 * 49 + (threadIdx_x_1 + 5) % 81 // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1120] = T.if_then_else(9 <= (threadIdx_x_1 + 67) % 81 and (threadIdx_x_1 + 67) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1120) // 81 * 49 + (threadIdx_x_1 + 67) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1344] = T.if_then_else(9 <= (threadIdx_x_1 + 48) % 81 and (threadIdx_x_1 + 48) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1344) // 81 * 49 + (threadIdx_x_1 + 48) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(9 <= (threadIdx_x_1 + 29) % 81 and (threadIdx_x_1 + 29) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 81 * 49 + (threadIdx_x_1 + 29) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 1792] = T.if_then_else(9 <= (threadIdx_x_1 + 10) % 81 and (threadIdx_x_1 + 10) % 81 < 72 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1792) // 81 * 49 + (threadIdx_x_1 + 10) % 81 // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 2016] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 8) % 9 and (threadIdx_x_1 + 72) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2016) // 81 * 49 + (threadIdx_x_1 // 9 + 8) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- pad_temp_shared_1[threadIdx_x_1 + 2240] = T.if_then_else(9 <= (threadIdx_x_1 + 53) % 81 and (threadIdx_x_1 + 53) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2240) // 81 * 49 + (threadIdx_x_1 + 53) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 224):
- if T.likely(threadIdx_x_1 < 128):
- pad_temp_shared_1[threadIdx_x_1 + 2464] = T.if_then_else(9 <= (threadIdx_x_1 + 34) % 81 and (threadIdx_x_1 + 34) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2464) // 81 * 49 + (threadIdx_x_1 + 34) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(9 <= (threadIdx_x_1 + 31) % 81 and (threadIdx_x_1 + 31) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ if T.likely(threadIdx_x_1 < 100):
+ pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((9216,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((1152,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 224):
- kernel_shared_1[threadIdx_x_2 * 16] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16]
- kernel_shared_1[threadIdx_x_2 * 16 + 1] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 1]
- kernel_shared_1[threadIdx_x_2 * 16 + 2] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 2]
- kernel_shared_1[threadIdx_x_2 * 16 + 3] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 3]
- kernel_shared_1[threadIdx_x_2 * 16 + 4] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 4]
- kernel_shared_1[threadIdx_x_2 * 16 + 5] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 5]
- kernel_shared_1[threadIdx_x_2 * 16 + 6] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 6]
- kernel_shared_1[threadIdx_x_2 * 16 + 7] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 7]
- kernel_shared_1[threadIdx_x_2 * 16 + 8] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 8]
- kernel_shared_1[threadIdx_x_2 * 16 + 9] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 9]
- kernel_shared_1[threadIdx_x_2 * 16 + 10] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 10]
- kernel_shared_1[threadIdx_x_2 * 16 + 11] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 11]
- kernel_shared_1[threadIdx_x_2 * 16 + 12] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 12]
- kernel_shared_1[threadIdx_x_2 * 16 + 13] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 13]
- kernel_shared_1[threadIdx_x_2 * 16 + 14] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 14]
- kernel_shared_1[threadIdx_x_2 * 16 + 15] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 16 + 15]
- with T.launch_thread(threadIdx_x_2, 224):
- kernel_shared_1[threadIdx_x_2 * 16 + 3584] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 128) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3585] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 129) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3586] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 130) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3587] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 131) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3588] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 132) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3589] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 133) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3590] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 134) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3591] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 135) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3592] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 136) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3593] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 137) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3594] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 138) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3595] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 139) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3596] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 140) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3597] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 141) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3598] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 142) % 288]
- kernel_shared_1[threadIdx_x_2 * 16 + 3599] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 143) % 288]
- with T.launch_thread(threadIdx_x_2, 224):
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7168] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 256) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7169] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 257) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7170] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 258) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7171] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 259) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7172] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 260) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7173] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 261) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7174] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 262) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7175] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 263) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7176] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 264) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7177] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 265) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7178] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 266) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7179] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 267) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7180] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 268) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7181] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 269) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7182] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 270) % 288]
- if T.likely(threadIdx_x_2 < 128):
- kernel_shared_1[threadIdx_x_2 * 16 + 7183] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 16 + 271) % 288]
- for rc_outer_inner, rx_outer_inner in T.grid(2, 3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 9]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 144] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 12]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 144] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 153] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 15]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 162] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 171] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 18]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 171] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 225] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 21]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 225] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 234] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 24]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 243] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 27]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 306] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 30]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 306] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 33]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 324] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 333] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 36]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 333] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 387] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 39]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 387] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 396] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 42]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 405] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 414] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 45]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 414] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 468] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 48]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 468] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 477] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 51]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 486] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 495] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 513] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 522] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 531] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 540] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 54]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 495] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 513] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 522] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 531] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 540] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 549] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 57]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 513] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 522] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 531] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 540] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 549] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 558] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 60]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 576] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 585] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 594] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 603] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 612] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 621] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 63]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 576] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 585] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 594] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 603] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 612] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 621] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 66]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 585] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 594] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 603] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 612] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 621] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 639] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 69]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 648] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 657] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 666] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 675] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 684] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 702] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 72]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 657] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 666] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 675] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 684] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 702] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 711] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 75]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 666] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 675] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 684] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 702] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 711] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 720] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 78]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 729] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 738] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 747] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 765] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 774] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 783] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 81]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 738] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 747] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 765] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 774] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 783] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 792] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 84]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 747] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 765] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 774] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 783] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 792] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 801] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 87]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 810] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 828] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 837] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 846] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 855] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 864] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 90]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 828] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 837] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 846] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 855] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 864] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 873] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 93]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 828] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 837] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 846] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 855] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 864] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 873] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 96]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 891] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 900] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 909] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 918] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 927] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 936] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 99]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 900] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 909] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 918] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 927] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 936] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 954] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 102]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 909] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 918] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 927] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 936] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 954] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 963] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 105]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 972] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 981] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 990] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 999] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1017] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1026] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 108]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 981] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 990] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 999] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1017] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1026] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1035] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 111]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 990] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 999] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1017] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1026] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1035] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1044] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 114]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1053] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1062] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1080] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1089] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1098] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1107] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 117]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1062] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1080] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1089] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1098] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1107] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1116] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 120]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1080] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1089] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1098] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1107] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1116] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1125] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 123]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1143] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1152] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1161] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1170] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1179] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1188] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 126]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1143] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1152] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1161] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1170] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1179] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1188] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 129]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1152] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1161] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1170] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1179] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1188] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1206] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 132]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1215] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1224] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1233] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1242] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1251] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1269] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 135]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1224] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1233] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1242] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1251] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1269] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1278] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 138]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1233] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1242] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1251] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1269] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1278] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1296 + rx_outer_inner + threadIdx_x % 7 + 1287] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_outer_inner * 144 + rx_outer_inner + 141]
- compute_1 = T.Buffer((25088,), data=compute.data)
- bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7] = T.max(conv2d_nchw_1[0] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 7] = T.max(conv2d_nchw_1[1] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 14] = T.max(conv2d_nchw_1[2] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 21] = T.max(conv2d_nchw_1[3] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 28] = T.max(conv2d_nchw_1[4] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 35] = T.max(conv2d_nchw_1[5] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 49 + threadIdx_x % 7 + 42] = T.max(conv2d_nchw_1[6] + bias_1[blockIdx_x * 32 + threadIdx_x // 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 2]
+ kernel_shared_1[threadIdx_x_2 * 2 + 1] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18 * 2 + 1]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 224] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 112) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 225] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 112) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 9) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 448] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 449] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 17) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 672] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 336) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 24) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 673] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 336) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 25) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 * 2 + 896] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 32) % 36]
+ kernel_shared_1[threadIdx_x_2 * 2 + 897] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 33) % 36]
+ with T.launch_thread(threadIdx_x_2, 112):
+ if T.likely(threadIdx_x_2 < 16):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1120] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 560) // 18 * 4608 + cse_var_1 + threadIdx_x_2 * 2 + 4]
+ if T.likely(threadIdx_x_2 < 16):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1121] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 560) // 18 * 4608 + cse_var_1 + threadIdx_x_2 * 2 + 5]
+ for rc_outer_inner, ff_outer_inner, rc_inner in T.grid(2, 2, 2):
+ cse_var_9: T.int32 = ff_outer_inner * 7
+ cse_var_8: T.int32 = cse_var_9 + 6
+ cse_var_7: T.int32 = cse_var_9 + 5
+ cse_var_6: T.int32 = cse_var_9 + 4
+ cse_var_5: T.int32 = cse_var_9 + 3
+ cse_var_4: T.int32 = cse_var_9 + 2
+ cse_var_3: T.int32 = cse_var_9 + 1
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 1]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 2]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 3]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 4]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 5]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 6]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 7]
+ conv2d_nchw_1[cse_var_9] = conv2d_nchw_1[cse_var_9] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_3] = conv2d_nchw_1[cse_var_3] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_4] = conv2d_nchw_1[cse_var_4] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_5] = conv2d_nchw_1[cse_var_5] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_6] = conv2d_nchw_1[cse_var_6] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_7] = conv2d_nchw_1[cse_var_7] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ conv2d_nchw_1[cse_var_8] = conv2d_nchw_1[cse_var_8] + pad_temp_shared_1[rc_outer_inner * 162 + rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 72 + ff_outer_inner * 36 + rc_outer_inner * 18 + rc_inner * 9 + 8]
+ for i1_inner, i2_inner in T.grid(2, 7):
+ compute_1 = T.Buffer((25088,), data=compute.data)
+ bias_1 = T.Buffer((512,), data=bias.data)
+ compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner * 7 + i2_inner] + bias_1[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -1003,7 +674,7 @@ class Module:
<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: 0.235 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.298 ms
</pre></div>
</div>
</div>
@@ -1033,33 +704,33 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
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_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=32)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
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_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=32)
+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=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
-compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=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=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
@@ -1079,16 +750,16 @@ 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=16)
+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=2)
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=224)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
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=224)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1106,10 +777,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[9216];
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1117,451 +788,112 @@ extern "C" __global__ void __launch_bounds__(224) default_function_ker
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((9 <= ((((int)threadIdx.x) + 10) % 81)) && (((((int)threadIdx.x) + 10) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + ((((((int)threadIdx.x) + 10) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 128) {
- pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 100) {
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
}
- kernel_shared[(((int)threadIdx.x) * 16)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16))];
- kernel_shared[((((int)threadIdx.x) * 16) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 16) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 16) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 3)];
- kernel_shared[((((int)threadIdx.x) * 16) + 4)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 4)];
- kernel_shared[((((int)threadIdx.x) * 16) + 5)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 5)];
- kernel_shared[((((int)threadIdx.x) * 16) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 6)];
- kernel_shared[((((int)threadIdx.x) * 16) + 7)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 7)];
- kernel_shared[((((int)threadIdx.x) * 16) + 8)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 8)];
- kernel_shared[((((int)threadIdx.x) * 16) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 9)];
- kernel_shared[((((int)threadIdx.x) * 16) + 10)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 10)];
- kernel_shared[((((int)threadIdx.x) * 16) + 11)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 11)];
- kernel_shared[((((int)threadIdx.x) * 16) + 12)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 12)];
- kernel_shared[((((int)threadIdx.x) * 16) + 13)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 13)];
- kernel_shared[((((int)threadIdx.x) * 16) + 14)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 14)];
- kernel_shared[((((int)threadIdx.x) * 16) + 15)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 18) * 16)) + 15)];
- kernel_shared[((((int)threadIdx.x) * 16) + 3584)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 128) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3585)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 129) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3586)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 130) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3587)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 131) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3588)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 132) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3589)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 133) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3590)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 134) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3591)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 135) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3592)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 136) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3593)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 137) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3594)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 138) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3595)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 139) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3596)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 140) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3597)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 141) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3598)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 142) % 288))];
- kernel_shared[((((int)threadIdx.x) * 16) + 3599)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 143) % 288))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7168)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 256) % 288))];
+ kernel_shared[(((int)threadIdx.x) * 2)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 18) * 2))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 18) * 2)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 2) + 224)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 8) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 225)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 9) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 448)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 16) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 449)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 17) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 672)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 24) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 673)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 25) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 896)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 32) % 36))];
+ kernel_shared[((((int)threadIdx.x) * 2) + 897)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) * 2) + 33) % 36))];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 2) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) * 2)) + 4)];
}
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7169)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 257) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7170)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 258) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7171)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 259) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7172)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 260) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7173)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 261) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7174)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 262) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7175)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 263) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7176)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 264) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7177)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 265) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7178)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 266) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7179)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 267) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7180)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 268) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7181)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 269) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7182)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 270) % 288))];
- }
- if (((int)threadIdx.x) < 128) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7183)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) + 271) % 288))];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 2) + 1121)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) * 2)) + 5)];
}
__syncthreads();
for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 42)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 51)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 57)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 60)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 63)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 66)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 69)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 711)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 720)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 81)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 84)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 792)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 801)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 87)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 90)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 93)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 873)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 954)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 963)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 108)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1035)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 111)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1035)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1044)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 114)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 117)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1116)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 120)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1116)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1125)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 123)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 126)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 129)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1206)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 132)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 135)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1278)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 138)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1278)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1296) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1287)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 144)) + rx_outer_inner) + 141)]));
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9))]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + (rc_inner * 81)) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (ff_outer_inner * 36)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + 8)]));
+ }
}
}
}
- compute[(((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
+ }
}
</pre></div>
</div>
@@ -1595,7 +927,7 @@ 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> ( 6 minutes 2.332 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 14.515 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 1bb875dfdc..3ee7029f74 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8959 7.8996 7.9098 7.8783 0.0131
+ 7.8876 7.8866 7.8967 7.8795 0.0070
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ 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 8.047 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.481 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 82323ce4d2..98bc58e0c5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -940,7 +940,7 @@ 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)
- 748.7372 748.0161 750.2849 747.9105 1.0953
+ 757.5129 755.1987 762.1745 755.1656 3.2962
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ 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 42.569 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 47.121 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 2e69345d66..7f8953af8c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,26 +637,75 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_outer_inner, nb_j_inner in T.grid(8, 2):
- for i_inner_init, j_init in T.grid(4, 16):
- compute_2[i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 4, 16):
- cse_var_1 = T.int32()
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_2: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16 + j
- placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
- placeholder_7 = T.Buffer((32768,), data=placeholder.data)
- placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 8192 + i_outer_inner * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner in range(32):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
- compute_3 = T.Buffer((65536,), data=compute.data)
- placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
+ for i0_outer in T.parallel(2):
+ compute_1 = T.allocate([2048], "float32", "global")
+ for i1_outer in range(16):
+ compute_2 = T.Buffer((2048,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(16, 2):
+ for i_inner_init in range(4):
+ cse_var_1: T.int32 = i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16
+ compute_2[cse_var_1] = T.float32(0)
+ compute_2[cse_var_1 + 1] = T.float32(0)
+ compute_2[cse_var_1 + 2] = T.float32(0)
+ compute_2[cse_var_1 + 3] = T.float32(0)
+ compute_2[cse_var_1 + 4] = T.float32(0)
+ compute_2[cse_var_1 + 5] = T.float32(0)
+ compute_2[cse_var_1 + 6] = T.float32(0)
+ compute_2[cse_var_1 + 7] = T.float32(0)
+ compute_2[cse_var_1 + 8] = T.float32(0)
+ compute_2[cse_var_1 + 9] = T.float32(0)
+ compute_2[cse_var_1 + 10] = T.float32(0)
+ compute_2[cse_var_1 + 11] = T.float32(0)
+ compute_2[cse_var_1 + 12] = T.float32(0)
+ compute_2[cse_var_1 + 13] = T.float32(0)
+ compute_2[cse_var_1 + 14] = T.float32(0)
+ compute_2[cse_var_1 + 15] = T.float32(0)
+ for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i1_outer * 2 + nb_j_inner}), 4):
+ cse_var_2 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i1_outer * 2 + nb_j_inner
+ cse_var_19: T.int32 = i0_outer * 16384 + i_outer_inner * 1024 + i_inner * 256
+ cse_var_18: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16
+ cse_var_17: T.int32 = cse_var_18 + 9
+ cse_var_16: T.int32 = cse_var_18 + 8
+ cse_var_15: T.int32 = cse_var_18 + 7
+ cse_var_14: T.int32 = cse_var_18 + 6
+ cse_var_13: T.int32 = cse_var_18 + 5
+ cse_var_12: T.int32 = cse_var_18 + 4
+ cse_var_11: T.int32 = cse_var_18 + 3
+ cse_var_10: T.int32 = cse_var_18 + 2
+ cse_var_9: T.int32 = cse_var_18 + 15
+ cse_var_8: T.int32 = cse_var_18 + 14
+ cse_var_7: T.int32 = cse_var_18 + 13
+ cse_var_6: T.int32 = cse_var_18 + 12
+ cse_var_5: T.int32 = cse_var_18 + 11
+ cse_var_4: T.int32 = cse_var_18 + 10
+ cse_var_3: T.int32 = cse_var_18 + 1
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(64, 32):
+ cse_var_22: T.int32 = i0_outer * 32768 + i0_inner * 512 + i1_outer * 32 + i1_inner
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ compute_3[cse_var_22] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_22], T.float32(0))
</pre></div>
</div>
</div>
@@ -690,7 +739,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.460 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.964 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 08b0e9d5de..1dbb440379 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:46.686</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:48.473</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,7 +354,7 @@
</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>00:46.650</p></td>
+<td><p>00:48.437</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>
@@ -366,7 +366,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
-<td><p>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
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 dfd8115da9..d824c594b9 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -695,7 +695,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9319783
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8828472
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -818,8 +818,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1855297
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1329391
+No: 3 GFLOPS: 101.53/101.53 result: MeasureResult(costs=(0.0022801618679245284,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8529009819030762, timestamp=1678344053.1014893) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3307932
+No: 4 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -941,26 +942,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7875377
-No: 4 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, 32, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8726377
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1410168
+No: 5 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1082,8 +1065,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5546995
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10372282
+No: 6 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1205,9 +1188,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8929719
-No: 7 GFLOPS: 5.45/5.45 result: MeasureResult(costs=(0.042468505749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.280545949935913, timestamp=1678321445.854263) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3693244
-No: 8 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10348246
+No: 7 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1329,8 +1311,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3447303
-No: 9 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4784229
+No: 8 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1452,131 +1434,161 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6836343
-No: 10 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2068700
+No: 9 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007fbd9826cfa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h:1621
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2769782
-No: 11 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
+
+Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7944121
+No: 10 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1698,8 +1710,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4146053
-No: 12 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1569880
+No: 11 GFLOPS: 37.54/101.53 result: MeasureResult(costs=(0.006166648411764706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3040320873260498, timestamp=1678344066.3975585) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,655438
+No: 12 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1821,8 +1834,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6141551
-No: 13 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7151729
+No: 13 GFLOPS: 3.89/101.53 result: MeasureResult(costs=(0.05952210225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.798225402832031, timestamp=1678344075.3766592) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9298467
+No: 14 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1944,8 +1958,9 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6546831
-No: 14 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,792053
+No: 15 GFLOPS: 77.32/101.53 result: MeasureResult(costs=(0.0029941216226415097,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.99426531791687, timestamp=1678344076.4028218) [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8917302
+No: 16 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2067,8 +2082,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3347534
-No: 15 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5606092
+No: 17 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2190,163 +2205,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5237374
-No: 16 GFLOPS: 0.00/5.45 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f2ef633ffa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4685999
-No: 17 GFLOPS: 110.53/110.53 result: MeasureResult(costs=(0.0020944786041666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.464320421218872, timestamp=1678321455.9058175) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2332914
-No: 18 GFLOPS: 5.84/110.53 result: MeasureResult(costs=(0.0396171035,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.570124864578247, timestamp=1678321456.8276098) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1675584
-No: 19 GFLOPS: 0.00/110.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5634724
+No: 18 GFLOPS: 3.96/101.53 result: MeasureResult(costs=(0.058526657,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.256460189819336, timestamp=1678344078.8579617) [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5818500
+No: 19 GFLOPS: 2.69/101.53 result: MeasureResult(costs=(0.08609279625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1326193809509277, timestamp=1678344080.4110823) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,36280
+No: 20 GFLOPS: 0.00/101.53 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2468,8 +2330,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2690307
-No: 20 GFLOPS: 70.03/110.53 result: MeasureResult(costs=(0.0033057994791666663,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.140754461288452, timestamp=1678321457.8515878) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8590461
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5015272
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2508,9 +2369,9 @@ 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, 1, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2332914
+[('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3307932
Finish loading 20 records
-Time cost of this operator: 0.001143
+Time cost of this operator: 0.002310
</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 e4da91acb0..2137ea4615 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -648,10 +648,10 @@ 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 316.7 98.75 (1, 2, 10, 10, 3) 2 1 [316.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.04 0.948 (1, 6, 10, 10) 1 1 [3.04]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.302 (1, 1, 10, 10, 3) 1 1 [0.969]
-Total_time - 320.709 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.3 98.718 (1, 2, 10, 10, 3) 2 1 [317.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.135 0.975 (1, 6, 10, 10) 1 1 [3.135]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.987 0.307 (1, 1, 10, 10, 3) 1 1 [0.987]
+Total_time - 321.422 - - - - -
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ 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 105.6 97.553 (1, 6, 10, 10, 1) 2 1 [105.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.658 (1, 6, 10, 10) 1 1 [1.795]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.854 0.789 (1, 3, 10, 10, 1) 1 1 [0.854]
-Total_time - 108.249 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.0 97.518 (1, 6, 10, 10, 1) 2 1 [103.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.781 1.686 (1, 6, 10, 10) 1 1 [1.781]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.795 (1, 3, 10, 10, 1) 1 1 [0.84]
+Total_time - 105.621 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.220 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.555 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.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_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 2afb796589..b008ab6b11 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -459,7 +459,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 51.8MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 181MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -585,7 +585,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.320 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.824 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 5152c45533..1a65971a7b 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -528,7 +528,7 @@ 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/tmpxnt1lmd2/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpvvg03l7i/images/random'
</pre></div>
</div>
</div>
@@ -588,8 +588,8 @@ 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], [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/tmpxnt1lmd2/images/target contains 8144 images
-/tmp/tmpxnt1lmd2/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [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], [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/tmpvvg03l7i/images/target contains 8144 images
+/tmp/tmpvvg03l7i/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -701,13 +701,13 @@ 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 - 50s - loss: 0.2173 - accuracy: 0.9237 - val_loss: 0.1207 - val_accuracy: 0.9554 - 50s/epoch - 153ms/step
+328/328 - 48s - loss: 0.2087 - accuracy: 0.9258 - val_loss: 0.1165 - val_accuracy: 0.9596 - 48s/epoch - 148ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.1044 - accuracy: 0.9610 - val_loss: 0.1016 - val_accuracy: 0.9596 - 44s/epoch - 133ms/step
+328/328 - 45s - loss: 0.1042 - accuracy: 0.9584 - val_loss: 0.1054 - val_accuracy: 0.9600 - 45s/epoch - 137ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0710 - accuracy: 0.9743 - val_loss: 0.0954 - val_accuracy: 0.9656 - 43s/epoch - 132ms/step
+328/328 - 44s - loss: 0.0623 - accuracy: 0.9765 - val_loss: 0.1018 - val_accuracy: 0.9607 - 44s/epoch - 135ms/step
-<keras.callbacks.History object at 0x7fb57c591890>
+<keras.callbacks.History object at 0x7fd06d52de90>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 46.662 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 35.263 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 544b480e3e..4b4650fabf 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>07:48.333</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:45.411</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,23 +354,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">5. 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>04:46.662</p></td>
+<td><p>04:35.263</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">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:23.220</p></td>
+<td><p>01:26.555</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:20.320</p></td>
+<td><p>01:24.824</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.441</p></td>
+<td><p>00:11.065</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.690</p></td>
+<td><p>00:07.705</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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">7. 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 ac31097eff..2a05e54e2c 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:47.316</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:50.158</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,19 +354,19 @@
</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>00:34.076</p></td>
+<td><p>00:37.651</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>00:11.320</p></td>
+<td><p>00:10.597</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>00:01.914</p></td>
+<td><p>00:01.903</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>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 919ff1a980..843001e048 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -540,7 +540,7 @@ 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 0x7fb4902c4830>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fcf7e573710>
</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 b87fe9bffc..353d5c9590 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:08.797</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.949</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.972</p></td>
+<td><p>00:04.270</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>00:01.448</p></td>
+<td><p>00:01.189</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>00:00.584</p></td>
+<td><p>00:00.633</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>00:00.562</p></td>
+<td><p>00:00.604</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.118</p></td>
+<td><p>00:00.126</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>00:00.052</p></td>
+<td><p>00:00.062</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>00:00.035</p></td>
+<td><p>00:00.036</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.027</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 89a2dbef47..de9a595da6 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -234,7 +234,17 @@
<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 b8d3c9aae2..0a6b8d6912 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1621,7 +1621,7 @@ 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>
@@ -1905,7 +1905,7 @@ 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 de17259fc2..f34962f31b 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/1453fe078/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/1453fe078/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/1453fe078/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L44">rpc_server.ts:44</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/1453fe078/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L65">rpc_server.ts:65</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/1453fe078/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L51">rpc_server.ts:51</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/1453fe078/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L59">rpc_server.ts:59</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 16dc632d89..8222a08b44 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/1453fe078/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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 697d46eeb2..0aef32b0f0 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/1453fe078/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L359">runtime.ts:359</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/1453fe078/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L357">runtime.ts:357</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/1453fe078/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L355">runtime.ts:355</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/1453fe078/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L359">runtime.ts:359</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/1453fe078/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L376">runtime.ts:376</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/1453fe078/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L367">runtime.ts:367</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 d5e7d0d88d..0b1af4b7cc 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/1453fe078/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L299">runtime.ts:299</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/1453fe078/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L297">runtime.ts:297</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/1453fe078/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L295">runtime.ts:295</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/1453fe078/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L320">runtime.ts:320</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/1453fe078/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L327">runtime.ts:327</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 a413c63d7c..a44c5193dc 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/1453fe078/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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 a3fd73f27c..b5c071ed12 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/1453fe078/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L50">runtime.ts:50</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/1453fe078/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L47">runtime.ts:47</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/1453fe078/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L46">runtime.ts:46</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/1453fe078/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L45">runtime.ts:45</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/1453fe078/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L48">runtime.ts:48</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/1453fe078/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L77">runtime.ts:77</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/1453fe078/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L67">runtime.ts:67</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/1453fe078/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L85">runtime.ts:85</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/1453fe078/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L96">runtime.ts:96</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/1453fe078/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L73">runtime.ts:73</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/instance.html b/docs/reference/api/typedoc/classes/instance.html
index b213060824..fb6a532750 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<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/1453fe078/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<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/1453fe078/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L957">runtime.ts:957</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 1edc2b6435..ee0137c624 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/1453fe078/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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 6e9ac7aba1..e47138ec8a 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.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/1453fe078/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L641">runtime.ts:641</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/1453fe078/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L687">runtime.ts:687</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 541f081efd..7a3b3dca52 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/1453fe078/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L401">runtime.ts:401</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/1453fe078/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L394">runtime.ts:394</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/1453fe078/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<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/1453fe078/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<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/1453fe078/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L553">runtime.ts:553</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 ec02b625f2..2f092e75c3 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index d958406c39..9627bee53d 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/1453fe078/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L95">rpc_server.ts:95</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/1453fe078/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L84">rpc_server.ts:84</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/1453fe078/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L80">rpc_server.ts:80</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/1453fe078/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L83">rpc_server.ts:83</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/1453fe078/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L81">rpc_server.ts:81</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/1453fe078/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L82">rpc_server.ts:82</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/1453fe078/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 18a18783c2..326587e94e 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index e2f2a66d10..70d257f732 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/1453fe078/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L235">runtime.ts:235</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/1453fe078/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L235">runtime.ts:235</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/1453fe078/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index 733ce69a25..ccbc173d7c 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L730">runtime.ts:730</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/1453fe078/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index beff7558c2..daa6899eeb 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.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/1453fe078/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L730">runtime.ts:730</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/1453fe078/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L758">runtime.ts:758</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 eb31f7d55d..31a28a7ccb 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/1453fe078/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/webgpu.ts#L172">webgpu.ts:172</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/1453fe078/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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 83bed2e1d8..9d983fd980 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/1453fe078/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L242">ctypes.ts:242</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/1453fe078/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L238">ctypes.ts:238</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/1453fe078/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L236">ctypes.ts:236</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/1453fe078/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L240">ctypes.ts:240</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/1453fe078/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L248">ctypes.ts:248</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/1453fe078/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L243">ctypes.ts:243</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/1453fe078/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L241">ctypes.ts:241</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/1453fe078/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L245">ctypes.ts:245</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/1453fe078/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L249">ctypes.ts:249</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/1453fe078/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L244">ctypes.ts:244</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/1453fe078/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L250">ctypes.ts:250</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/1453fe078/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L239">ctypes.ts:239</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/1453fe078/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L246">ctypes.ts:246</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/1453fe078/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L247">ctypes.ts:247</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/1453fe078/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 75a56e59e9..c94b572ad1 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/1453fe078/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L812">runtime.ts:812</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/1453fe078/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 866f204351..8856ea31d0 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/1453fe078/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L339">runtime.ts:339</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/1453fe078/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L337">runtime.ts:337</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/1453fe078/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L340">runtime.ts:340</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/1453fe078/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 1af1bb4e3a..23addda299 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/1453fe078/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L29">rpc_server.ts:29</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/1453fe078/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L30">rpc_server.ts:30</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/1453fe078/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L31">rpc_server.ts:31</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/1453fe078/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L34">rpc_server.ts:34</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/1453fe078/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L33">rpc_server.ts:33</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/1453fe078/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index f31835558e..8ec863d22c 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/1453fe078/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L228">ctypes.ts:228</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/1453fe078/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L229">ctypes.ts:229</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/1453fe078/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L225">ctypes.ts:225</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/1453fe078/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L226">ctypes.ts:226</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/1453fe078/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L223">ctypes.ts:223</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/1453fe078/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L224">ctypes.ts:224</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/1453fe078/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L227">ctypes.ts:227</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/1453fe078/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L222">ctypes.ts:222</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/1453fe078/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 515cfbc381..8fba15dc60 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<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>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<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/1453fe078/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<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/1453fe078/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<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/1453fe078/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<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/1453fe078/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<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/1453fe078/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<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/1453fe078/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<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/1453fe078/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<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/1453fe078/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<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/1453fe078/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<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/1453fe078/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<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/1453fe078/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<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/1453fe078/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<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/1453fe078/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<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/1453fe078/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<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/1453fe078/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<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/1453fe078/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<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/1453fe078/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<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/1453fe078/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<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"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<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><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<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"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<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/1453fe078/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<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/1453fe078/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<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/1453fe078/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<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/1453fe078/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<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/1453fe078/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<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/1453fe078/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<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/1453fe078/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<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/1453fe078/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<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/1453fe078/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<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/1453fe078/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<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/1453fe078/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/1453fe078/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<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/1453fe078/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<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/1453fe078/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<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/1453fe078/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<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/1453fe078/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<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/1453fe078/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<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/1453fe078/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<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/1453fe078/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<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/1453fe078/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<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/1453fe078/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<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/1453fe078/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<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/1453fe078/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<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/1453fe078/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<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/1453fe078/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<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/1453fe078/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<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/1453fe078/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<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/1453fe078/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<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/1453fe078/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<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/1453fe078/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<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/1453fe078/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index f3f30d8bdf..3ca2fe2330 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<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/1453fe078/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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 803850da1e..81774a2496 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/1453fe078/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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 25b71a683a..df1834dd4e 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/1453fe078/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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/1453fe078/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6b4e3d08e/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 efd32f2101..130ba82f97 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 d39c926705..5fff905bfb 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:32.222</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:33.724</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,7 +354,7 @@
</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>00:32.215</p></td>
+<td><p>00:33.717</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 0b2759baa1..c4adf726ca 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -588,7 +588,7 @@ 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 34.35s!
+resnet18_v1 inference graph built in 35.50s!
</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 5d1c467f34..9b3301e155 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -606,7 +606,7 @@ 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 23.34s!
+yolov3-tiny inference graph built in 23.90s!
</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 5b7e6823dc..565d09e574 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:41.841</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:43.492</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><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>00:51.290</p></td>
+<td><p>00:52.419</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:50.551</p></td>
+<td><p>00:51.073</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 dec62b51ab..8267dbd313 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:03.167</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.194</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</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>00:02.697</p></td>
+<td><p>00:02.706</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>00:00.470</p></td>
+<td><p>00:00.488</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 8cf1f3cde9..6502393116 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:00.788</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.819</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,11 +354,11 @@
</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>00:00.413</p></td>
+<td><p>00:00.421</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>00:00.375</p></td>
+<td><p>00:00.397</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index a90759a767..52a7a54307 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -574,7 +574,7 @@ class Module:
<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: 96.648 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.437 ms
</pre></div>
</div>
</div>
@@ -646,7 +646,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.223 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.203 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 fa785291dd..6b59462352 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -685,16 +685,16 @@ 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: 2.14/2.14 result: MeasureResult(costs=(0.12535433619999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2580337524414062, timestamp=1678319862.0638366) [('tile_y', [-1, 8]), ('tile_x', [-1, 2])],None,13
-No: 2 GFLOPS: 10.41/10.41 result: MeasureResult(costs=(0.025796567,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6771280765533447, timestamp=1678319862.737913) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
-No: 3 GFLOPS: 8.68/10.41 result: MeasureResult(costs=(0.030932515,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8485634326934814, timestamp=1678319864.7239118) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
-No: 4 GFLOPS: 10.06/10.41 result: MeasureResult(costs=(0.0266719474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7474157810211182, timestamp=1678319866.6362557) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
-No: 5 GFLOPS: 2.66/10.41 result: MeasureResult(costs=(0.10097175600000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8504841327667236, timestamp=1678319868.621185) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
-No: 6 GFLOPS: 11.51/11.51 result: MeasureResult(costs=(0.0233234726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6312999725341797, timestamp=1678319870.4712865) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
-No: 7 GFLOPS: 0.51/11.51 result: MeasureResult(costs=(0.5246637655999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.635518550872803, timestamp=1678319879.1259377) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
-No: 8 GFLOPS: 2.20/11.51 result: MeasureResult(costs=(0.12208912219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.199854850769043, timestamp=1678319881.3336918) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
-No: 9 GFLOPS: 10.36/11.51 result: MeasureResult(costs=(0.0259004844,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6367299556732178, timestamp=1678319882.0872421) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 10 GFLOPS: 10.65/11.51 result: MeasureResult(costs=(0.0251954118,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6173386573791504, timestamp=1678319882.749092) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+No: 1 GFLOPS: 2.61/2.61 result: MeasureResult(costs=(0.1027501444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8946588039398193, timestamp=1678342380.7743597) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 2 GFLOPS: 1.24/2.61 result: MeasureResult(costs=(0.21638905519999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6978631019592285, timestamp=1678342384.4965248) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
+No: 3 GFLOPS: 1.55/2.61 result: MeasureResult(costs=(0.1726559244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.001988410949707, timestamp=1678342388.821764) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+No: 4 GFLOPS: 10.42/10.42 result: MeasureResult(costs=(0.0257712914,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6560153961181641, timestamp=1678342390.7604556) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+No: 5 GFLOPS: 1.99/10.42 result: MeasureResult(costs=(0.1350411852,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.399169683456421, timestamp=1678342393.2936676) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+No: 6 GFLOPS: 3.04/10.42 result: MeasureResult(costs=(0.0884382058,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6885795593261719, timestamp=1678342396.2553372) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+No: 7 GFLOPS: 2.50/10.42 result: MeasureResult(costs=(0.107351902,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.952357530593872, timestamp=1678342398.2266138) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
+No: 8 GFLOPS: 0.90/10.42 result: MeasureResult(costs=(0.299787507,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.028179407119751, timestamp=1678342403.2741692) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+No: 9 GFLOPS: 10.45/10.45 result: MeasureResult(costs=(0.025699142200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6684181690216064, timestamp=1678342404.056666) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
+No: 10 GFLOPS: 3.09/10.45 result: MeasureResult(costs=(0.08673808920000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6067490577697754, timestamp=1678342405.7035344) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
</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 f07b9ad3e1..f930b70864 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -563,7 +563,7 @@ 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': 510.5504202200018, 'median': 510.6422028499992, 'std': 1.665563049841246}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 520.8213620399988, 'median': 520.6977899499975, 'std': 2.7301109700505735}
</pre></div>
</div>
</div>
@@ -715,178 +715,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 8.52/ 17.46 GFLOPS | Progress: (4/20) | 12.11 s
-[Task 1/25] Current/Best: 14.79/ 17.46 GFLOPS | Progress: (8/20) | 16.33 s
-[Task 1/25] Current/Best: 22.82/ 23.61 GFLOPS | Progress: (12/20) | 18.59 s
-[Task 1/25] Current/Best: 15.00/ 23.61 GFLOPS | Progress: (16/20) | 21.32 s
-[Task 1/25] Current/Best: 19.14/ 23.61 GFLOPS | Progress: (20/20) | 23.48 s Done.
+[Task 1/25] Current/Best: 6.75/ 13.19 GFLOPS | Progress: (4/20) | 12.64 s
+[Task 1/25] Current/Best: 14.20/ 22.00 GFLOPS | Progress: (8/20) | 15.30 s
+[Task 1/25] Current/Best: 21.52/ 22.00 GFLOPS | Progress: (12/20) | 17.92 s
+[Task 1/25] Current/Best: 15.07/ 22.00 GFLOPS | Progress: (16/20) | 20.15 s
+[Task 1/25] Current/Best: 10.94/ 22.00 GFLOPS | Progress: (20/20) | 26.46 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 6.60/ 16.77 GFLOPS | Progress: (4/20) | 5.05 s
-[Task 2/25] Current/Best: 3.81/ 18.99 GFLOPS | Progress: (8/20) | 6.75 s
-[Task 2/25] Current/Best: 16.13/ 18.99 GFLOPS | Progress: (12/20) | 9.62 s
-[Task 2/25] Current/Best: 18.60/ 18.99 GFLOPS | Progress: (16/20) | 11.21 s
-[Task 2/25] Current/Best: 5.67/ 22.68 GFLOPS | Progress: (20/20) | 12.57 s Done.
+[Task 2/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 4.44 s
+[Task 2/25] Current/Best: 11.35/ 19.91 GFLOPS | Progress: (8/20) | 6.43 s
+[Task 2/25] Current/Best: 6.46/ 19.91 GFLOPS | Progress: (12/20) | 7.84 s
+[Task 2/25] Current/Best: 8.74/ 22.41 GFLOPS | Progress: (16/20) | 9.69 s
+[Task 2/25] Current/Best: 11.84/ 22.41 GFLOPS | Progress: (20/20) | 11.06 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 11.84/ 23.16 GFLOPS | Progress: (4/20) | 4.75 s
-[Task 3/25] Current/Best: 12.44/ 23.16 GFLOPS | Progress: (8/20) | 7.85 s
-[Task 3/25] Current/Best: 9.87/ 23.16 GFLOPS | Progress: (12/20) | 10.41 s
-[Task 3/25] Current/Best: 12.21/ 23.16 GFLOPS | Progress: (16/20) | 12.71 s
-[Task 3/25] Current/Best: 14.24/ 23.16 GFLOPS | Progress: (20/20) | 15.67 s Done.
+[Task 3/25] Current/Best: 13.04/ 13.04 GFLOPS | Progress: (4/20) | 5.54 s
+[Task 3/25] Current/Best: 8.51/ 19.16 GFLOPS | Progress: (8/20) | 7.91 s
+[Task 3/25] Current/Best: 17.88/ 19.16 GFLOPS | Progress: (12/20) | 10.37 s
+[Task 3/25] Current/Best: 5.08/ 19.90 GFLOPS | Progress: (16/20) | 12.79 s
+[Task 3/25] Current/Best: 16.89/ 19.90 GFLOPS | Progress: (20/20) | 15.11 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 16.79/ 21.27 GFLOPS | Progress: (4/20) | 4.83 s
-[Task 4/25] Current/Best: 8.24/ 21.27 GFLOPS | Progress: (8/20) | 6.92 s
-[Task 4/25] Current/Best: 21.28/ 21.28 GFLOPS | Progress: (12/20) | 15.03 s
-[Task 4/25] Current/Best: 19.43/ 21.28 GFLOPS | Progress: (16/20) | 16.78 s
-[Task 4/25] Current/Best: 6.40/ 21.28 GFLOPS | Progress: (20/20) | 21.27 s Done.
+[Task 4/25] Current/Best: 10.99/ 12.60 GFLOPS | Progress: (4/20) | 6.96 s
+[Task 4/25] Current/Best: 15.89/ 17.21 GFLOPS | Progress: (8/20) | 9.60 s
+[Task 4/25] Current/Best: 7.94/ 17.21 GFLOPS | Progress: (12/20) | 11.58 s
+[Task 4/25] Current/Best: 13.48/ 17.21 GFLOPS | Progress: (16/20) | 13.75 s
+[Task 4/25] Current/Best: 7.08/ 17.21 GFLOPS | Progress: (20/20) | 17.49 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 6.95/ 22.75 GFLOPS | Progress: (4/20) | 4.69 s
-[Task 5/25] Current/Best: 12.12/ 22.75 GFLOPS | Progress: (8/20) | 6.76 s
-[Task 5/25] Current/Best: 13.20/ 22.75 GFLOPS | Progress: (12/20) | 8.89 s
-[Task 5/25] Current/Best: 4.10/ 22.75 GFLOPS | Progress: (16/20) | 11.31 s
-[Task 5/25] Current/Best: 11.03/ 22.75 GFLOPS | Progress: (20/20) | 14.03 s Done.
+[Task 5/25] Current/Best: 11.85/ 18.78 GFLOPS | Progress: (4/20) | 5.08 s
+[Task 5/25] Current/Best: 17.82/ 18.78 GFLOPS | Progress: (8/20) | 6.94 s
+[Task 5/25] Current/Best: 16.25/ 18.78 GFLOPS | Progress: (12/20) | 8.75 s
+[Task 5/25] Current/Best: 11.73/ 18.78 GFLOPS | Progress: (16/20) | 11.42 s
+[Task 5/25] Current/Best: 10.82/ 18.78 GFLOPS | Progress: (20/20) | 13.98 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.64/ 17.76 GFLOPS | Progress: (4/20) | 6.57 s
-[Task 6/25] Current/Best: 3.12/ 17.76 GFLOPS | Progress: (8/20) | 10.25 s
-[Task 6/25] Current/Best: 14.16/ 17.76 GFLOPS | Progress: (12/20) | 12.46 s
-[Task 6/25] Current/Best: 1.59/ 18.11 GFLOPS | Progress: (16/20) | 16.20 s
-[Task 6/25] Current/Best: 10.90/ 18.11 GFLOPS | Progress: (20/20) | 19.16 s Done.
+[Task 6/25] Current/Best: 4.59/ 17.80 GFLOPS | Progress: (4/20) | 6.26 s
+[Task 6/25] Current/Best: 16.96/ 17.80 GFLOPS | Progress: (8/20) | 8.78 s
+[Task 6/25] Current/Best: 9.13/ 17.90 GFLOPS | Progress: (12/20) | 11.65 s
+[Task 6/25] Current/Best: 3.89/ 17.90 GFLOPS | Progress: (16/20) | 15.12 s
+[Task 6/25] Current/Best: 8.43/ 18.20 GFLOPS | Progress: (20/20) | 18.11 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.62/ 12.27 GFLOPS | Progress: (4/20) | 5.89 s
-[Task 7/25] Current/Best: 5.98/ 20.83 GFLOPS | Progress: (8/20) | 8.42 s
-[Task 7/25] Current/Best: 15.88/ 21.31 GFLOPS | Progress: (12/20) | 10.90 s
-[Task 7/25] Current/Best: 15.32/ 21.31 GFLOPS | Progress: (16/20) | 13.08 s
-[Task 7/25] Current/Best: 11.67/ 21.31 GFLOPS | Progress: (20/20) | 15.84 s Done.
+[Task 7/25] Current/Best: 16.30/ 16.86 GFLOPS | Progress: (4/20) | 5.49 s
+[Task 7/25] Current/Best: 15.93/ 20.63 GFLOPS | Progress: (8/20) | 7.70 s
+[Task 7/25] Current/Best: 9.38/ 20.63 GFLOPS | Progress: (12/20) | 11.05 s
+[Task 7/25] Current/Best: 19.00/ 20.63 GFLOPS | Progress: (16/20) | 13.15 s
+[Task 7/25] Current/Best: 16.20/ 20.63 GFLOPS | Progress: (20/20) | 15.58 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 11.23/ 12.82 GFLOPS | Progress: (4/20) | 7.77 s
-[Task 8/25] Current/Best: 10.11/ 20.21 GFLOPS | Progress: (8/20) | 10.39 s
-[Task 8/25] Current/Best: 13.06/ 20.21 GFLOPS | Progress: (12/20) | 22.17 s
-[Task 8/25] Current/Best: 5.22/ 20.21 GFLOPS | Progress: (16/20) | 25.95 s
-[Task 8/25] Current/Best: 5.64/ 20.21 GFLOPS | Progress: (20/20) | 28.96 s Done.
-
+[Task 8/25] Current/Best: 18.39/ 18.39 GFLOPS | Progress: (4/20) | 5.71 s
+[Task 8/25] Current/Best: 8.85/ 21.31 GFLOPS | Progress: (8/20) | 9.25 s
+[Task 8/25] Current/Best: 20.59/ 21.31 GFLOPS | Progress: (12/20) | 11.48 s
+[Task 8/25] Current/Best: 7.69/ 21.31 GFLOPS | Progress: (16/20) | 18.06 s
+[Task 8/25] Current/Best: 15.10/ 21.31 GFLOPS | Progress: (20/20) | 29.45 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 6.22/ 15.43 GFLOPS | Progress: (4/20) | 4.85 s
-[Task 9/25] Current/Best: 8.09/ 15.43 GFLOPS | Progress: (8/20) | 6.92 s
-[Task 9/25] Current/Best: 12.67/ 16.41 GFLOPS | Progress: (12/20) | 8.65 s
-[Task 9/25] Current/Best: 23.06/ 23.06 GFLOPS | Progress: (16/20) | 15.34 s
-[Task 9/25] Current/Best: 12.10/ 23.06 GFLOPS | Progress: (20/20) | 22.84 s Done.
+[Task 9/25] Current/Best: 18.90/ 23.69 GFLOPS | Progress: (4/20) | 6.54 s
+[Task 9/25] Current/Best: 11.59/ 23.69 GFLOPS | Progress: (8/20) | 9.35 s
+[Task 9/25] Current/Best: 8.21/ 23.69 GFLOPS | Progress: (12/20) | 13.14 s
+[Task 9/25] Current/Best: 10.34/ 23.69 GFLOPS | Progress: (16/20) | 21.33 s
+[Task 9/25] Current/Best: 12.29/ 23.69 GFLOPS | Progress: (20/20) | 23.36 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 15.09/ 15.90 GFLOPS | Progress: (4/20) | 5.25 s
-[Task 10/25] Current/Best: 11.08/ 21.31 GFLOPS | Progress: (8/20) | 6.91 s
-[Task 10/25] Current/Best: 16.13/ 21.31 GFLOPS | Progress: (12/20) | 8.97 s
-[Task 10/25] Current/Best: 8.53/ 21.31 GFLOPS | Progress: (16/20) | 11.06 s
-[Task 10/25] Current/Best: 11.32/ 21.31 GFLOPS | Progress: (20/20) | 13.28 s Done.
+[Task 10/25] Current/Best: 21.57/ 21.57 GFLOPS | Progress: (4/20) | 4.55 s
+[Task 10/25] Current/Best: 13.14/ 21.57 GFLOPS | Progress: (8/20) | 6.34 s Done.
+
+[Task 10/25] Current/Best: 11.96/ 21.57 GFLOPS | Progress: (12/20) | 8.84 s
+[Task 10/25] Current/Best: 11.08/ 21.57 GFLOPS | Progress: (16/20) | 11.09 s
+[Task 10/25] Current/Best: 9.28/ 21.57 GFLOPS | Progress: (20/20) | 13.18 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 15.42/ 18.15 GFLOPS | Progress: (4/20) | 5.41 s
-[Task 11/25] Current/Best: 12.90/ 18.15 GFLOPS | Progress: (8/20) | 8.40 s
-[Task 11/25] Current/Best: 23.74/ 23.74 GFLOPS | Progress: (12/20) | 10.57 s
-[Task 11/25] Current/Best: 11.33/ 23.74 GFLOPS | Progress: (16/20) | 13.74 s
-[Task 11/25] Current/Best: 19.39/ 23.74 GFLOPS | Progress: (20/20) | 16.24 s Done.
+[Task 11/25] Current/Best: 6.18/ 11.82 GFLOPS | Progress: (4/20) | 6.39 s
+[Task 11/25] Current/Best: 11.81/ 19.06 GFLOPS | Progress: (8/20) | 9.93 s
+[Task 11/25] Current/Best: 12.09/ 19.06 GFLOPS | Progress: (12/20) | 12.51 s
+[Task 11/25] Current/Best: 18.12/ 19.06 GFLOPS | Progress: (16/20) | 14.96 s
+[Task 11/25] Current/Best: 13.25/ 19.06 GFLOPS | Progress: (20/20) | 17.78 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 17.06/ 21.06 GFLOPS | Progress: (4/20) | 4.57 s
-[Task 12/25] Current/Best: 14.50/ 21.06 GFLOPS | Progress: (8/20) | 8.99 s
-[Task 12/25] Current/Best: 13.60/ 21.06 GFLOPS | Progress: (12/20) | 11.73 s
-[Task 12/25] Current/Best: 13.83/ 21.06 GFLOPS | Progress: (16/20) | 13.62 s
-[Task 12/25] Current/Best: 18.38/ 21.06 GFLOPS | Progress: (20/20) | 16.04 s Done.
+[Task 12/25] Current/Best: 10.63/ 13.07 GFLOPS | Progress: (4/20) | 8.80 s
+[Task 12/25] Current/Best: 1.60/ 22.05 GFLOPS | Progress: (8/20) | 12.55 s
+[Task 12/25] Current/Best: 17.58/ 22.05 GFLOPS | Progress: (12/20) | 14.81 s
+[Task 12/25] Current/Best: 9.35/ 22.05 GFLOPS | Progress: (16/20) | 17.55 s
+[Task 12/25] Current/Best: 13.02/ 22.05 GFLOPS | Progress: (20/20) | 20.86 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 17.40/ 19.80 GFLOPS | Progress: (4/20) | 5.74 s
-[Task 13/25] Current/Best: 12.16/ 19.80 GFLOPS | Progress: (8/20) | 8.96 s
-[Task 13/25] Current/Best: 19.35/ 19.80 GFLOPS | Progress: (12/20) | 11.90 s
-[Task 13/25] Current/Best: 16.67/ 19.80 GFLOPS | Progress: (16/20) | 14.20 s
-[Task 13/25] Current/Best: 15.55/ 19.80 GFLOPS | Progress: (20/20) | 16.96 s Done.
+[Task 13/25] Current/Best: 18.44/ 19.38 GFLOPS | Progress: (4/20) | 5.60 s
+[Task 13/25] Current/Best: 18.18/ 19.38 GFLOPS | Progress: (8/20) | 9.25 s
+[Task 13/25] Current/Best: 17.77/ 19.68 GFLOPS | Progress: (12/20) | 11.22 s
+[Task 13/25] Current/Best: 13.99/ 19.68 GFLOPS | Progress: (16/20) | 13.33 s
+[Task 13/25] Current/Best: 9.03/ 19.68 GFLOPS | Progress: (20/20) | 16.74 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 9.45/ 12.53 GFLOPS | Progress: (4/20) | 7.39 s
-[Task 14/25] Current/Best: 15.74/ 15.74 GFLOPS | Progress: (8/20) | 17.60 s
-[Task 14/25] Current/Best: 9.44/ 15.74 GFLOPS | Progress: (12/20) | 20.34 s
-[Task 14/25] Current/Best: 13.26/ 15.74 GFLOPS | Progress: (16/20) | 25.11 s
-[Task 14/25] Current/Best: 11.23/ 15.74 GFLOPS | Progress: (20/20) | 30.60 s
+[Task 14/25] Current/Best: 2.90/ 17.66 GFLOPS | Progress: (4/20) | 5.41 s
+[Task 14/25] Current/Best: 14.11/ 17.66 GFLOPS | Progress: (8/20) | 10.33 s
+[Task 14/25] Current/Best: 14.89/ 17.66 GFLOPS | Progress: (12/20) | 12.62 s
+[Task 14/25] Current/Best: 12.41/ 17.66 GFLOPS | Progress: (16/20) | 15.54 s
+[Task 14/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (20/20) | 19.32 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 5.81/ 18.23 GFLOPS | Progress: (4/20) | 11.68 s
-[Task 15/25] Current/Best: 13.45/ 21.36 GFLOPS | Progress: (8/20) | 17.13 s
-[Task 15/25] Current/Best: 18.29/ 21.36 GFLOPS | Progress: (12/20) | 23.29 s
-[Task 15/25] Current/Best: 18.43/ 21.36 GFLOPS | Progress: (16/20) | 24.94 s
-[Task 15/25] Current/Best: 13.84/ 21.36 GFLOPS | Progress: (20/20) | 26.94 s
+[Task 15/25] Current/Best: 13.93/ 13.93 GFLOPS | Progress: (4/20) | 4.83 s
+[Task 15/25] Current/Best: 6.49/ 19.87 GFLOPS | Progress: (8/20) | 7.75 s
+[Task 15/25] Current/Best: 18.10/ 19.87 GFLOPS | Progress: (12/20) | 9.98 s
+[Task 15/25] Current/Best: 15.75/ 19.87 GFLOPS | Progress: (16/20) | 14.95 s
+[Task 15/25] Current/Best: 9.55/ 19.87 GFLOPS | Progress: (20/20) | 21.15 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 4.71/ 14.25 GFLOPS | Progress: (4/20) | 5.83 s
-[Task 16/25] Current/Best: 10.71/ 15.31 GFLOPS | Progress: (8/20) | 8.09 s
-[Task 16/25] Current/Best: 10.37/ 15.83 GFLOPS | Progress: (12/20) | 10.35 s
-[Task 16/25] Current/Best: 12.15/ 19.14 GFLOPS | Progress: (16/20) | 14.05 s
-[Task 16/25] Current/Best: 15.48/ 19.14 GFLOPS | Progress: (20/20) | 16.06 s Done.
+[Task 16/25] Current/Best: 9.85/ 12.50 GFLOPS | Progress: (4/20) | 6.70 s
+[Task 16/25] Current/Best: 6.11/ 20.86 GFLOPS | Progress: (8/20) | 8.63 s
+[Task 16/25] Current/Best: 9.79/ 20.86 GFLOPS | Progress: (12/20) | 12.63 s
+[Task 16/25] Current/Best: 15.31/ 20.86 GFLOPS | Progress: (16/20) | 15.37 s
+[Task 16/25] Current/Best: 11.80/ 20.86 GFLOPS | Progress: (20/20) | 18.14 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.61/ 18.70 GFLOPS | Progress: (4/20) | 4.90 s
-[Task 17/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (8/20) | 8.89 s
-[Task 17/25] Current/Best: 18.97/ 19.31 GFLOPS | Progress: (12/20) | 11.60 s
-[Task 17/25] Current/Best: 13.23/ 19.31 GFLOPS | Progress: (16/20) | 14.07 s
-[Task 17/25] Current/Best: 6.40/ 19.31 GFLOPS | Progress: (20/20) | 17.76 s Done.
+[Task 17/25] Current/Best: 11.90/ 16.82 GFLOPS | Progress: (4/20) | 7.58 s
+[Task 17/25] Current/Best: 11.41/ 20.44 GFLOPS | Progress: (8/20) | 10.19 s
+[Task 17/25] Current/Best: 15.99/ 22.29 GFLOPS | Progress: (12/20) | 13.30 s
+[Task 17/25] Current/Best: 12.20/ 22.29 GFLOPS | Progress: (16/20) | 15.70 s
+[Task 17/25] Current/Best: 9.46/ 22.29 GFLOPS | Progress: (20/20) | 18.05 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 6.01/ 15.02 GFLOPS | Progress: (4/20) | 6.76 s
-[Task 18/25] Current/Best: 15.54/ 15.54 GFLOPS | Progress: (8/20) | 9.81 s
-[Task 18/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 12.36 s
-[Task 18/25] Current/Best: 5.78/ 19.05 GFLOPS | Progress: (16/20) | 14.84 s
-[Task 18/25] Current/Best: 14.89/ 19.05 GFLOPS | Progress: (20/20) | 16.90 s Done.
+[Task 18/25] Current/Best: 4.53/ 15.30 GFLOPS | Progress: (4/20) | 6.02 s
+[Task 18/25] Current/Best: 8.25/ 19.40 GFLOPS | Progress: (8/20) | 9.09 s
+[Task 18/25] Current/Best: 17.69/ 19.40 GFLOPS | Progress: (12/20) | 10.95 s
+[Task 18/25] Current/Best: 6.29/ 19.40 GFLOPS | Progress: (16/20) | 13.07 s
+[Task 18/25] Current/Best: 18.02/ 19.40 GFLOPS | Progress: (20/20) | 15.89 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 11.33/ 11.33 GFLOPS | Progress: (4/20) | 7.56 s
-[Task 19/25] Current/Best: 7.37/ 11.33 GFLOPS | Progress: (8/20) | 13.93 s
-[Task 19/25] Current/Best: 17.86/ 18.96 GFLOPS | Progress: (12/20) | 16.91 s
-[Task 19/25] Current/Best: 9.26/ 18.96 GFLOPS | Progress: (16/20) | 22.04 s
-[Task 19/25] Current/Best: 5.25/ 18.96 GFLOPS | Progress: (20/20) | 25.51 s Done.
+[Task 19/25] Current/Best: 13.14/ 22.73 GFLOPS | Progress: (4/20) | 6.60 s
+[Task 19/25] Current/Best: 20.98/ 22.73 GFLOPS | Progress: (8/20) | 9.07 s
+[Task 19/25] Current/Best: 12.39/ 22.73 GFLOPS | Progress: (12/20) | 11.81 s
+[Task 19/25] Current/Best: 22.27/ 22.73 GFLOPS | Progress: (16/20) | 15.41 s
+[Task 19/25] Current/Best: 19.43/ 22.73 GFLOPS | Progress: (20/20) | 18.24 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 10.50/ 20.28 GFLOPS | Progress: (4/20) | 5.02 s
-[Task 20/25] Current/Best: 9.72/ 20.28 GFLOPS | Progress: (8/20) | 8.04 s
-[Task 20/25] Current/Best: 15.06/ 20.28 GFLOPS | Progress: (12/20) | 10.78 s
-[Task 20/25] Current/Best: 10.10/ 21.64 GFLOPS | Progress: (16/20) | 15.57 s
-[Task 20/25] Current/Best: 3.91/ 21.64 GFLOPS | Progress: (20/20) | 19.24 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 13.65/ 19.72 GFLOPS | Progress: (4/20) | 5.64 s Done.
- Done.
- Done.
+[Task 20/25] Current/Best: 11.69/ 14.40 GFLOPS | Progress: (4/20) | 5.12 s
+[Task 20/25] Current/Best: 16.75/ 16.75 GFLOPS | Progress: (8/20) | 7.59 s
+[Task 20/25] Current/Best: 14.98/ 16.75 GFLOPS | Progress: (12/20) | 10.89 s Done.
-[Task 21/25] Current/Best: 16.15/ 19.72 GFLOPS | Progress: (8/20) | 7.90 s
-[Task 21/25] Current/Best: 14.13/ 19.72 GFLOPS | Progress: (12/20) | 11.64 s
-[Task 21/25] Current/Best: 9.07/ 21.47 GFLOPS | Progress: (16/20) | 14.21 s
-[Task 21/25] Current/Best: 15.80/ 21.47 GFLOPS | Progress: (20/20) | 17.77 s
+[Task 20/25] Current/Best: 10.48/ 16.75 GFLOPS | Progress: (16/20) | 17.69 s
+[Task 20/25] Current/Best: 17.67/ 17.67 GFLOPS | Progress: (20/20) | 19.86 s Done.
+
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 21/25] Current/Best: 5.25/ 17.42 GFLOPS | Progress: (4/20) | 4.82 s
+[Task 21/25] Current/Best: 19.63/ 19.63 GFLOPS | Progress: (8/20) | 7.81 s
+[Task 21/25] Current/Best: 11.72/ 22.38 GFLOPS | Progress: (12/20) | 10.43 s
+[Task 21/25] Current/Best: 2.53/ 22.38 GFLOPS | Progress: (16/20) | 13.66 s
+[Task 21/25] Current/Best: 10.70/ 22.53 GFLOPS | Progress: (20/20) | 16.23 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 12.57/ 12.57 GFLOPS | Progress: (4/20) | 4.66 s
-[Task 22/25] Current/Best: 12.06/ 16.77 GFLOPS | Progress: (8/20) | 6.85 s
-[Task 22/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (12/20) | 9.91 s
-[Task 22/25] Current/Best: 10.86/ 20.92 GFLOPS | Progress: (16/20) | 11.54 s
-[Task 22/25] Current/Best: 15.74/ 20.92 GFLOPS | Progress: (20/20) | 13.22 s Done.
+[Task 22/25] Current/Best: 16.30/ 17.97 GFLOPS | Progress: (4/20) | 5.68 s
+[Task 22/25] Current/Best: 8.94/ 17.97 GFLOPS | Progress: (8/20) | 10.20 s
+[Task 22/25] Current/Best: 5.35/ 17.97 GFLOPS | Progress: (12/20) | 12.25 s
+[Task 22/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (16/20) | 14.49 s
+[Task 22/25] Current/Best: 18.41/ 20.61 GFLOPS | Progress: (20/20) | 17.02 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 19.06/ 20.00 GFLOPS | Progress: (4/20) | 5.37 s
-[Task 23/25] Current/Best: 10.19/ 20.12 GFLOPS | Progress: (8/20) | 8.79 s
-[Task 23/25] Current/Best: 11.95/ 20.12 GFLOPS | Progress: (12/20) | 12.83 s
-[Task 23/25] Current/Best: 3.08/ 20.12 GFLOPS | Progress: (16/20) | 17.08 s
-[Task 23/25] Current/Best: 14.05/ 20.12 GFLOPS | Progress: (20/20) | 19.74 s Done.
+[Task 23/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (4/20) | 5.64 s
+[Task 23/25] Current/Best: 6.00/ 20.08 GFLOPS | Progress: (8/20) | 10.13 s
+[Task 23/25] Current/Best: 7.67/ 20.08 GFLOPS | Progress: (12/20) | 13.50 s
+[Task 23/25] Current/Best: 18.73/ 20.08 GFLOPS | Progress: (16/20) | 17.37 s
+[Task 23/25] Current/Best: 8.13/ 20.08 GFLOPS | Progress: (20/20) | 21.63 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 6.40/ 6.40 GFLOPS | Progress: (4/20) | 13.72 s
-[Task 24/25] Current/Best: 3.57/ 9.87 GFLOPS | Progress: (8/20) | 17.05 s
-[Task 24/25] Current/Best: 2.31/ 9.87 GFLOPS | Progress: (12/20) | 28.01 s
-[Task 24/25] Current/Best: 3.70/ 10.70 GFLOPS | Progress: (16/20) | 40.30 s
-[Task 24/25] Current/Best: 3.34/ 10.70 GFLOPS | Progress: (20/20) | 46.43 s
+[Task 24/25] Current/Best: 7.27/ 8.04 GFLOPS | Progress: (4/20) | 13.75 s
+[Task 24/25] Current/Best: 1.55/ 8.04 GFLOPS | Progress: (8/20) | 26.16 s
+[Task 24/25] Current/Best: 3.95/ 9.04 GFLOPS | Progress: (12/20) | 29.39 s
+[Task 24/25] Current/Best: 3.59/ 9.04 GFLOPS | Progress: (16/20) | 34.55 s
+[Task 24/25] Current/Best: 8.19/ 9.76 GFLOPS | Progress: (20/20) | 45.21 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
-[Task 25/25] Current/Best: 1.55/ 6.95 GFLOPS | Progress: (4/20) | 5.26 s
-[Task 25/25] Current/Best: 8.52/ 9.34 GFLOPS | Progress: (8/20) | 10.29 s
-[Task 25/25] Current/Best: 8.82/ 9.34 GFLOPS | Progress: (12/20) | 11.64 s
-[Task 25/25] Current/Best: 5.95/ 9.34 GFLOPS | Progress: (16/20) | 13.08 s
-[Task 25/25] Current/Best: 4.61/ 9.34 GFLOPS | Progress: (20/20) | 24.03 s
+[Task 25/25] Current/Best: 2.86/ 9.03 GFLOPS | Progress: (4/20) | 13.73 s
+[Task 25/25] Current/Best: 5.86/ 9.03 GFLOPS | Progress: (8/20) | 17.97 s
+[Task 25/25] Current/Best: 7.29/ 9.03 GFLOPS | Progress: (12/20) | 22.94 s
+[Task 25/25] Current/Best: 1.55/ 9.03 GFLOPS | Progress: (16/20) | 33.90 s
+[Task 25/25] Current/Best: 5.56/ 9.03 GFLOPS | Progress: (20/20) | 36.86 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -947,9 +948,9 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
-class='n02123159 tiger cat' with probability=0.356379
-class='n02124075 Egyptian cat' with probability=0.019712
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
+class='n02123159 tiger cat' with probability=0.356377
+class='n02124075 Egyptian cat' with probability=0.019713
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
</pre></div>
@@ -985,8 +986,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 417.13500321999845, 'median': 415.84399574999225, 'std': 3.0956879571744502}
-unoptimized: {'mean': 510.5504202200018, 'median': 510.6422028499992, 'std': 1.665563049841246}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 432.349127399998, 'median': 433.6005759499926, 'std': 5.591029240686418}
+unoptimized: {'mean': 520.8213620399988, 'median': 520.6977899499975, 'std': 2.7301109700505735}
</pre></div>
</div>
</div>
@@ -1000,7 +1001,7 @@ 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> ( 12 minutes 21.345 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 19.074 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 f2ac68f379..104f98b183 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -543,7 +543,7 @@ 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>1.259e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.271e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 23c3f5df34..ff4075fa53 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -513,7 +513,7 @@ class Module:
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x21801380)), stage(b, placeholder(b, 0x23dd0ef0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attr [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xa81c8a0)), stage(b, placeholder(b, 0x2214beb0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index b151023084..f5c6e5454c 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:43.002</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>16:06.908</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>12:21.345</p></td>
+<td><p>12:19.074</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:13.223</p></td>
+<td><p>01:33.203</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.149</p></td>
+<td><p>01:01.652</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:36.243</p></td>
+<td><p>00:36.954</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:29.416</p></td>
+<td><p>00:33.433</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.619</p></td>
+<td><p>00:01.535</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.844</p></td>
+<td><p>00:00.872</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.162</p></td>
+<td><p>00:00.186</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index b0b89891c0..ad5783ef60 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -555,7 +555,7 @@ helper function to run a profile of the TVM generated code.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000009
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -649,7 +649,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000031
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -686,10 +686,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 6.8646999989141475e-06 1.0
- naive 9.327e-06 1.3586901104892184
-parallel 6.9454000000000005e-06 1.0117557942952522
- vector 2.4621e-05 3.5866097577307863
+ numpy 7.299419999071688e-06 1.0
+ naive 6.783699999999999e-06 0.9293478113141488
+parallel 6.9638e-06 0.9540210045298981
+ vector 3.0512899999999997e-05 4.18018143960486
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1005,7 +1005,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017811
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018837
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1046,7 +1046,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.355344
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.453174
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1110,7 +1110,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.292092
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.295932
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1159,7 +1159,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.347297
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.336475
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1208,7 +1208,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116573
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.119338
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1278,7 +1278,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109130
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110082
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1344,7 +1344,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.109929
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111686
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1401,7 +1401,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146105
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146865
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.3553441144 1.0
- blocking 0.2920919691 0.08705276095123606
- vectorization 0.34729719340000004 0.10350568572371406
-loop permutation 0.1165725155 0.03474234281953683
- array packing 0.10912982280000001 0.03252418204489125
- block caching 0.10992877109999999 0.03276229422437566
- parallelization 0.14610499329999999 0.04354396697285589
+ none 3.4531739437999995 1.0
+ blocking 0.2959322071 0.0856986100081438
... 17 lines suppressed ...