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 2023/02/03 09:51:41 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@209f074e96a654bd1830de1c769ee3d7c4c01bd2)
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 bee81a9c93 deploying docs (apache/tvm@209f074e96a654bd1830de1c769ee3d7c4c01bd2)
bee81a9c93 is described below
commit bee81a9c93c29d44b8a44abc66b8ec1b373fb33c
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Feb 3 09:51:35 2023 +0000
deploying docs (apache/tvm@209f074e96a654bd1830de1c769ee3d7c4c01bd2)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 339681 -> 330018 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24019 -> 24252 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 | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1065 ++------------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 85 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 680 +++++++++----
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../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 | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 52 +-
.../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 | 43 +-
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 | 14 +-
docs/how_to/compile_models/from_pytorch.html | 13 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 50 +-
docs/how_to/deploy_models/deploy_prequantized.html | 10 +-
.../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 | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1064 ++-----------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 85 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 680 +++++++++----
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 10 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 268 ++---
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 | 39 +-
129 files changed, 2181 insertions(+), 3089 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 3bff224219..c4e860d6e8 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 45939926ac..b77852b4c4 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 0bd68fff80..b1e356fff7 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 19.041 seconds)
+ **Total running time of the script:** ( 1 minutes 16.700 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 c27b36a73f..ef1b2f5575 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 976ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 947ms/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 dcbea4f78c..68b90e4cc4 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.zipdf0b6226-bfb2-416d-b47d-d24a74034118 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4def1531-ec12-4f36-b69c-49a5180c35ec 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 f73af83a48..be60848583 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]
15%|#5 | 6.33M/41.5M [00:00<00:00, 51.3MB/s]
27%|##7 | 11.2M/41.5M [00:00<00:00, 50.1MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 35.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 46.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 52.8MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 51.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 49.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 39.9MB/s]
24%|##4 | 10.1M/41.5M [00:00<00:01, 26.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:01, 26.2MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 25.4MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 19.0MB/s]
96%|#########6| 40.0M/41.5M [00:01<00:00, 25.0MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 25.4MB/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 506551e501..ffb61c4e8e 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]
19%|#9 | 8.55M/44.7M [00:00<00:00, 89.6MB/s]
38%|###8 | 17.1M/44.7M [00:00<00:00, 85.2MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 83.7MB/s]
78%|#######7 | 34.7M/44.7M [00:00<00:00, 86.1MB/s]
96%|#########6| 42.9M/44.7M [00:00<00:00, 83.4MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 78.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.30M/44.7M [00:00<00:00, 46.7MB/s]
24%|##4 | 10.8M/44.7M [00:00<00:01, 30.8MB/s]
48%|####7 | 21.4M/44.7M [00:00<00:00, 56.7MB/s]
65%|######5 | 29.2M/44.7M [00:00<00:00, 62.9MB/s]
81%|######## | 36.0M/44.7M [00:00<00:00, 46.0MB/s]
93%|#########2| 41.4M/44.7M [00:00<00:00, 46.9MB/s]
100%|##########| 44.7M/44.7M [00:01<00:00, 46.7MB/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 d641d59385..b9ced6a18a 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 24.705 seconds)
+ **Total running time of the script:** ( 1 minutes 21.828 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 4271085578..cbcb5e75f0 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
=================
-**06:33.801** total execution time for **how_to_compile_models** files:
+**06:24.226** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:24.705 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:21.828 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:19.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:16.700 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:53.630 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:52.403 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.700 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.379 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:31.730 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.540 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.260 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:30.202 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.736 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.236 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.899 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.967 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:21.410 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:21.362 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.690 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.608 | 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 fcb85d1170..36bfe6f29d 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)
- 2689.0542 2688.5836 2693.3420 2687.1370 1.6496
+ 2682.1442 2681.3672 2686.9123 2680.1429 2.2582
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 e078c5efaa..0da3a01be2 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)
- 16.7706 16.8533 17.1930 16.0958 0.3462
+ 15.5065 15.4865 15.6432 15.4388 0.0652
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 38751791b4..83c1453fe7 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]
5%|4 | 7.89M/170M [00:00<00:02, 82.7MB/s]
9%|9 | 15.8M/170M [00:00<00:02, 67.7MB/s]
13%|#3 | 22.4M/170M [00:00<00:03, 49.9MB/s]
16%|#6 | 27.6M/170M [00:00<00:03, 44.6MB/s]
21%|## | 35.2M/170M [00:00<00:02, 54.2MB/s]
25%|##4 | 42.1M/170M [00:00<00:02, 50.4MB/s]
29%|##8 | 49.0M/170M [00:00<00:02, 56.0MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 57.2MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 63.1MB/s]
44%|####3 | 74.1M/170M [00:01<00:01, 73.4MB/s]
48%|####7 | 81.3M/170M [00:01<00:01, 65.5MB/s]
52%|#####2 | 88.5M/170M [00:01<00:01, 68.0MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 62.3MB/s]
61%|######1 | 104M/170M [00:01<00:01, 65.5MB/s]
66%|######6 | 113M/170M [00:01<00:00, 70.1MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 89.0MB/s]
80%|######## | 136M/170M [00:02<00:00, 74.1MB/s]
85%|########4 | 144M/170M [00:02<00:00, 72.4MB/s]
89%|########9 | 152M/170M [00:02<00:00, 74.1MB/s]
94%|#########4| 160M/170M [00:02<00:00, 71.3MB/s]
98%|#########8| 167M/170M [00:02<00:00, 67.3MB/s]
100%|##########| 170M/170M [00:02<00:00, 64.3MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:04, 42.6MB/s]
8%|8 | 14.3M/170M [00:00<00:03, 52.8MB/s]
12%|#1 | 19.6M/170M [00:00<00:02, 53.8MB/s]
15%|#4 | 24.8M/170M [00:00<00:03, 47.0MB/s]
18%|#7 | 30.3M/170M [00:00<00:02, 49.8MB/s]
21%|## | 35.2M/170M [00:00<00:03, 43.8MB/s]
24%|##3 | 40.0M/170M [00:00<00:03, 42.6MB/s]
27%|##7 | 46.2M/170M [00:01<00:02, 48.5MB/s]
31%|###1 | 53.2M/170M [00:01<00:02, 54.9MB/s]
35%|###4 | 58.6M/170M [00:01<00:02, 50.2MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 48.9MB/s]
43%|####3 | 73.2M/170M [00:01<00:01, 61.5MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 62.6MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 60.0MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 56.2MB/s]
61%|######1 | 104M/170M [00:02<00:01, 53.0MB/s]
66%|######5 | 112M/170M [00:02<00:01, 54.5MB/s
]
71%|####### | 120M/170M [00:02<00:00, 60.7MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 58.2MB/s]
79%|#######8 | 134M/170M [00:02<00:00, 53.6MB/s]
82%|########1 | 139M/170M [00:02<00:00, 53.9MB/s]
85%|########5 | 144M/170M [00:02<00:00, 54.7MB/s]
89%|########9 | 152M/170M [00:02<00:00, 59.2MB/s]
95%|#########4| 161M/170M [00:03<00:00, 68.1MB/s]
99%|#########8| 168M/170M [00:03<00:00, 66.2MB/s]
100%|##########| 170M/170M [00:03<00:00, 56.1MB/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 34.346 seconds)
+ **Total running time of the script:** ( 3 minutes 20.248 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 3275c91647..3d45331205 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, 46.0MB/s]
91%|#########1| 12.4M/13.6M [00:00<00:00, 45.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 49.1MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 50.2MB/s]
94%|#########4| 12.8M/13.6M [00:00<00:00, 49.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 52.1MB/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)
- 90.2701 90.2320 91.1414 90.1097 0.1864
+ 90.1649 89.9985 94.8026 89.8245 0.6398
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 15.782 seconds)
+ **Total running time of the script:** ( 1 minutes 12.337 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 4e172df19a..e9528177b4 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)
- 119.3250 119.3362 119.9164 118.5386 0.3018
+ 116.5960 116.3894 121.0563 115.7927 0.6959
@@ -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 34.085 seconds)
+ **Total running time of the script:** ( 2 minutes 32.389 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 5895cd9956..f7434e7d05 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 47.374 seconds)
+ **Total running time of the script:** ( 1 minutes 42.073 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 502cd8bd5a..1bc9f0dfad 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]
5%|4 | 6345/132723 [00:00<00:01, 63445.83KB/s]
11%|# | 13964/132723 [00:00<00:01, 70932.59KB/s]
17%|#6 | 22044/132723 [00:00<00:01, 75436.33KB/s]
23%|##2 | 30085/132723 [00:00<00:01, 77396.06KB/s]
29%|##8 | 38161/132723 [00:00<00:01, 78601.09KB/s]
35%|###4 | 46233/132723 [00:00<00:01, 79313.04KB/s]
41%|#### | 54323/132723 [00:00<00:00, 79829.69KB/s]
47%|####6 | 62306/132723 [00:00<00:00, 79110.79KB/s]
53%|#####2 | 70219/132723 [00:00<00:00, 78695.90KB/s]
59%|#####8 | 78090/132723 [00:01<00:00, 78193.21KB/s]
65%|######4 | 85911/132723 [00:01<00:00, 78030.63KB/s]
71%|####### | 93715/132723 [00:01<00:00, 77866.39KB/s]
76%|#######6 | 101503/132723 [00:01<00:00, 77839.64KB/s]
82%|########2 | 109310/132723 [00:01<00:00, 77906.74KB/s]
88%|########8 | 117101/132723 [00:01<00:00, 77696.10KB/s]
94%|########
#4| 124871/132723 [00:01<00:00, 77658.07KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77644.07KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77547.17KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7040/132723 [00:00<00:01, 70396.21KB/s]
12%|#1 | 15676/132723 [00:00<00:01, 79783.27KB/s]
18%|#8 | 24367/132723 [00:00<00:01, 83030.90KB/s]
25%|##4 | 32685/132723 [00:00<00:01, 83085.72KB/s]
31%|###1 | 41324/132723 [00:00<00:01, 84271.20KB/s]
38%|###7 | 49956/132723 [00:00<00:00, 84965.27KB/s]
44%|####4 | 58623/132723 [00:00<00:00, 85520.77KB/s]
51%|##### | 67176/132723 [00:00<00:00, 83810.69KB/s]
57%|#####7 | 75881/132723 [00:00<00:00, 84808.04KB/s]
64%|######3 | 84538/132723 [00:01<00:00, 85343.72KB/s]
70%|####### | 93289/132723 [00:01<00:00, 86000.02KB/s]
77%|#######6 | 102026/132723 [00:01<00:00, 86412.90KB/s]
83%|########3 | 110760/132723 [00:01<00:00, 86690.60KB/s]
90%|######### | 119537/132723 [00:01<00:00, 87014.21KB/s]
97%|#########6| 128313/132723 [00:01<00:00, 87235.29KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 85093.56KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 37.969 seconds)
+ **Total running time of the script:** ( 3 minutes 29.198 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 90ee8c5783..9541c516bf 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
=================
-**15:22.671** total execution time for **how_to_deploy_models** files:
+**14:44.345** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:37.969 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:29.198 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:34.346 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:20.248 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:34.085 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:32.389 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:47.374 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.073 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:15.782 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:12.337 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.779 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.771 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:41.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:39.572 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.077 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.011 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.621 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.740 | 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 fddf803544..628fb123f9 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.zip171c635f-144d-48e4-8541-bccc31b7e39e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip0571037d-2a89-43fa-bbdf-71397d663765 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 c9b2262ba3..a47d0df11d 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
=================
-**00:54.065** total execution time for **how_to_extend_tvm** files:
+**00:51.590** 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``) | 00:50.161 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:47.907 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.787 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.636 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.109 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.038 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index ab65776bf3..05bd3dbd2c 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: 21141us [21141us] (48.64%; 48.64%)
- FoldScaleAxis: 22323us [8us] (51.36%; 51.36%)
- FoldConstant: 22315us [1704us] (51.34%; 99.97%)
- InferType: 20611us [20611us] (47.42%; 92.36%)
+ InferType: 21025us [21025us] (48.63%; 48.63%)
+ FoldScaleAxis: 22205us [7us] (51.37%; 51.37%)
+ FoldConstant: 22199us [1674us] (51.35%; 99.97%)
+ InferType: 20525us [20525us] (47.48%; 92.46%)
@@ -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: 20666us [20666us] (48.06%; 48.06%)
- FoldScaleAxis: 22331us [7us] (51.94%; 51.94%)
- FoldConstant: 22324us [1720us] (51.92%; 99.97%)
- InferType: 20603us [20603us] (47.92%; 92.29%)
+ InferType: 20580us [20580us] (48.44%; 48.44%)
+ FoldScaleAxis: 21906us [5us] (51.56%; 51.56%)
+ FoldConstant: 21902us [1663us] (51.55%; 99.98%)
+ InferType: 20239us [20239us] (47.64%; 92.41%)
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 d216af742e..61141d727d 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: 50.327518 ms
+ Convolution: 45.987808 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 d719eb7ec7..0ff285e99e 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
@@ -608,7 +608,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.019635 ms
+ conv2d with tensor core: 10.568201 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 72e26c4e03..ece0dabc3f 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: 0.018697
- Baseline: 3.386919
+ Numpy running time: 0.017640
+ Baseline: 3.298908
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.307382
+ Opt1: 0.301587
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.340299
+ Opt2: 0.334763
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118252
+ Opt3: 0.113063
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109058
+ Opt4: 0.108578
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.112386
+ Opt5: 0.110367
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147332
+ Opt6: 0.145990
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 89649d4cfb..4025207b45 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
=================
-**00:35.118** total execution time for **how_to_optimize_operators** files:
+**00:34.320** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.480 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.765 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.547 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.501 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.090 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.054 | 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 eb25fb2a8f..43d20ef0fc 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
=================
-**09:24.856** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:21.729** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:39.782 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:43.646 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:40.825 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:37.989 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:07.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:05.003 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.042 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.091 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.222 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.435 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.779 | 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 18baa24923..fe079bc93b 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
@@ -244,487 +244,72 @@ 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.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 32)
+ T.launch_thread(blockIdx_x, 64)
conv2d_nchw = T.allocate([8], "float32", "local")
- pad_temp_shared = T.allocate([2016], "float32", "shared")
- kernel_shared = T.allocate([1536], "float32", "shared")
+ pad_temp_shared = T.allocate([3136], "float32", "shared")
+ kernel_shared = T.allocate([512], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 98)
- conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
+ T.launch_thread(threadIdx_x, 49)
+ conv2d_nchw_1 = T.Buffer((16,), data=conv2d_nchw, scope="local", align=16)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[3] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(16, 3):
- cse_var_4: T.int32 = rc_outer_outer * 1568
- cse_var_3: T.int32 = rc_outer_outer * 288
- cse_var_2: T.int32 = ry_outer_outer * 7
+ for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(8, 3, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 576
cse_var_1: T.int32 = ry_outer_outer * 3
+ pad_temp_shared_1 = T.Buffer((3136,), data=pad_temp_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(64):
+ cse_var_3: T.int32 = ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49
+ threadIdx_x_1 = T.env_thread("threadIdx.x")
+ T.launch_thread(threadIdx_x_1, 49)
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[cse_var_3 + threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 // 7 + ry_outer_outer and threadIdx_x_1 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 3136 + cse_var_3 + ry_outer_outer * 7 + rx_outer_outer + threadIdx_x_1 - 8], T.float32(0))
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((2016,), data=pad_temp_shared, scope="shared")
- data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 * 12] = T.if_then_else(1 <= threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer < 8 and 0 < threadIdx_x_1 % 3, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1] = T.if_then_else(1 <= threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer < 8, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 7], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 2] = T.if_then_else(1 <= threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer < 8 and threadIdx_x_1 % 3 < 2, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 6], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 3] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 3) % 9 and (threadIdx_x_1 * 3 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 4] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 4) % 9 and (threadIdx_x_1 * 3 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 5] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 5) % 9 and (threadIdx_x_1 * 3 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 5) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 6] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 6) % 9 and (threadIdx_x_1 * 3 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 2) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 7] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 7) % 9 and (threadIdx_x_1 * 3 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 2) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 8] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 8) % 9 and (threadIdx_x_1 * 3 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 2) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 8) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 9] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 < 8 and 0 < threadIdx_x_1 % 3, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 1], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 10] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 < 8, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 11] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 < 8 and threadIdx_x_1 % 3 < 2, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 1], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 6) % 9 and (threadIdx_x_1 * 3 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 6) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1177] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 7) % 9 and (threadIdx_x_1 * 3 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 7) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1178] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 8) % 9 and (threadIdx_x_1 * 3 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 8) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1179] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 < 8 and 0 < threadIdx_x_1 % 3, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 909], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1180] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 < 8, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 910], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1181] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 < 8 and threadIdx_x_1 % 3 < 2, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 911], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1182] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 3) % 9 and (threadIdx_x_1 * 3 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 394) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 3) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1183] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 4) % 9 and (threadIdx_x_1 * 3 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 394) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 4) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1184] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 5) % 9 and (threadIdx_x_1 * 3 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 394) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 5) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1185] = T.if_then_else(1 <= ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 and ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 < 8 and 1 < (threadIdx_x_1 * 3 + 6) % 9 and (threadIdx_x_1 * 3 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 6) % 9 - 1], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1186] = T.if_then_else(1 <= ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 and ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 < 8 and 1 <= (threadIdx_x_1 * 3 + 7) % 9 and (threadIdx_x_1 * 3 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 7) % 9 - 1], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1187] = T.if_then_else(1 <= ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 and ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 < 8 and 1 < (threadIdx_x_1 * 3 + 8) % 9 and (threadIdx_x_1 * 3 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 8) % 9 - 1], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((1536,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((512,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 32 * 4608 + cse_var_3 + threadIdx_x_2 % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 32 * 4608 + cse_var_3 + threadIdx_x_2 % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 32 * 4608 + cse_var_3 + threadIdx_x_2 % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 294] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 2) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 295] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 2) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 296] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 2) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 588] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 4) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 589] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 4) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 590] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 4) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 882] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 6) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 883] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 6) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 884] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 6) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 1176] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1177] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1178] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- if T.likely(threadIdx_x_2 < 22):
- kernel_shared_1[threadIdx_x_2 * 3 + 1470] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 10) * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1471] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 10) * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1472] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 10) * 9 + cse_var_1 + 2]
- for rc_outer_inner in range(2):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 384]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 768]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1152]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 96]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 480]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 864]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1248]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 385]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 769]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1153]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 97]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 481]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 865]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1249]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 386]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 770]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1154]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 98]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 482]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 866]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1250]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 387]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 771]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1155]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 99]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 483]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 867]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1251]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 388]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 772]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1156]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 100]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 484]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 868]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1252]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 5]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 389]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 773]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1157]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 101]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 485]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 869]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1253]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 390]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 774]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1158]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 102]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 486]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 870]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1254]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 7]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 391]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 775]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1159]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 103]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 487]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 871]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1255]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 8]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 392]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 776]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1160]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 104]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 488]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 872]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1256]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 393]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 777]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1161]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 105]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 489]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 873]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1257]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 10]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 394]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 778]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1162]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 106]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 490]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 874]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1258]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 11]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 395]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 779]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1163]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 107]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 491]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 875]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1259]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 396]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 780]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1164]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 108]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 492]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 876]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1260]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 13]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 397]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 781]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1165]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 109]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 493]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 877]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1261]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 14]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 398]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 782]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1166]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 110]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 494]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 878]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1262]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 399]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 783]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1167]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 111]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 495]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 879]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1263]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 16]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 400]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 784]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1168]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 112]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 496]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 880]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1264]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 17]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 401]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 785]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1169]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 113]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 497]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 881]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1265]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 402]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 786]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1170]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 114]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 498]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 882]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1266]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 19]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 403]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 787]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1171]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 115]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 499]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 883]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1267]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 20]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 404]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 788]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1172]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 116]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 500]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 884]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1268]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 405]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 789]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1173]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 117]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 501]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 885]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1269]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 22]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 406]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 790]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1174]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 118]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 502]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 886]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1270]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 23]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 407]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 791]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1175]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 119]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 503]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 887]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1271]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 24]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 408]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 792]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1176]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 120]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 504]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 888]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1272]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 25]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 409]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 793]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1177]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 121]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 505]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 889]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1273]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 26]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 410]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 794]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1178]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 122]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 506]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 890]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1274]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 27]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 411]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 795]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1179]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 123]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 507]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 891]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1275]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 28]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 412]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 796]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1180]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 124]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 508]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 892]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1276]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 29]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 413]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 797]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1181]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 125]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 509]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 893]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1277]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 30]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 414]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 798]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1182]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 126]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 510]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 894]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1278]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 31]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 415]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 799]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1183]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 127]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 511]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 895]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1279]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 32]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 416]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 800]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1184]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 128]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 512]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 896]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1280]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 33]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 417]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 801]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1185]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 129]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 513]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 897]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1281]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 34]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 418]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 802]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1186]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 130]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 514]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 898]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1282]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 35]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 419]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 803]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1187]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 131]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 515]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 899]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1283]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 36]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 420]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 804]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1188]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 132]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 516]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 900]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1284]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 37]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 421]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 805]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1189]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 133]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 517]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 901]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1285]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 38]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 422]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 806]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1190]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 134]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 518]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 902]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1286]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 39]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 423]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 807]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1191]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 135]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 519]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 903]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1287]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 40]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 424]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 808]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1192]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 136]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 520]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 904]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1288]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 41]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 425]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 809]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1193]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 137]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 521]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 905]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1289]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 42]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 426]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 810]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1194]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 138]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 522]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 906]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1290]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 43]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 427]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 811]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1195]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 139]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 523]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 907]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1291]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 44]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 428]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 812]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1196]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 140]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 524]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 908]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1292]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 45]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 429]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 813]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1197]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 141]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 525]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 909]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1293]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 46]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 430]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 814]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1198]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 142]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 526]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 910]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1294]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 47]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 431]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 815]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1199]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 143]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 527]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 911]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1295]
- for i1_inner in range(2):
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x * 36864 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 49] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 49) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 49) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 98] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 98) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 34) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 147] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 147) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 19) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 196] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 196) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 4) * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 245] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 245) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 53) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 294] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 294) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 38) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 343] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 343) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 23) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 392] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 392) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 441] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 441) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 57) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ if T.likely(threadIdx_x_1 < 22):
+ kernel_shared_1[threadIdx_x_1 + 490] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 490) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 42) * 9 + cse_var_1 + rx_outer_outer]
+ for rc_outer_inner, rc_inner in T.grid(8, 8):
+ cse_var_4: T.int32 = rc_outer_inner * 8 + rc_inner
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 256]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 64]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 320]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 128]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 384]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 192]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 448]
+ for i1_inner in range(4):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49 + 196] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner + 4], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49 + 392] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner + 8], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49 + 588] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner + 12], T.float32(0))
+ compute_1[blockIdx_x * 392 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 8 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + i1_inner * 49 + threadIdx_x + 196] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 8 + i1_inner + 4], T.float32(0))
@@ -774,7 +359,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.237 ms
+ Execution time of this operator: 0.240 ms
@@ -822,10 +407,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
@@ -834,19 +419,19 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=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=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -869,16 +454,16 @@ 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=3)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=12)
+ 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=98)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -896,483 +481,57 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[1536];
+ __shared__ float pad_temp_shared[3136];
+ __shared__ float kernel_shared[512];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 12)] = ((((1 <= ((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer) < 8)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((1 <= ((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = ((((1 <= ((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7)) < 8)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3))] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7)) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 1)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1178)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1179)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7)) < 8)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 909)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1180)] = (((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 910)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1181)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7)) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 911)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1182)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1183)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1184)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1185)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1186)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1187)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 1)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 2) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 295)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 2) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 296)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 2) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 589)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 590)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 6) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 883)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 6) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 884)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 6) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1177)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1178)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- if (((int)threadIdx.x) < 22) {
- kernel_shared[((((int)threadIdx.x) * 3) + 1470)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 90)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1471)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 91)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1472)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 384)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 768)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1152)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 480)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 864)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1248)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 385)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 769)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1153)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 481)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 865)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1249)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 386)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 770)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1154)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 482)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 866)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1250)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 387)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 771)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1155)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 483)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 867)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1251)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 388)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 772)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1156)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 484)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 868)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1252)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 389)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 773)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1157)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 485)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 869)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1253)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 390)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 774)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1158)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 486)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 870)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1254)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 391)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 775)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1159)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 103)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 487)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 871)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1255)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 392)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 776)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1160)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 104)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 488)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 872)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1256)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 393)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 777)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1161)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 489)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 873)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1257)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 394)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 778)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1162)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 106)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 490)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 874)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1258)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 395)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 779)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1163)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 107)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 491)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 875)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1259)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 396)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 780)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1164)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 492)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 876)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1260)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 397)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 781)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1165)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 109)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 493)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 877)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1261)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 398)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 782)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1166)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 110)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 494)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 878)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1262)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 399)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 783)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1167)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 111)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 495)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 879)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1263)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 400)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 784)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1168)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 112)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 496)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 880)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1264)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 401)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 785)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1169)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 113)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 497)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 881)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1265)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 402)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 786)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1170)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 114)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 498)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 882)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1266)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 403)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 787)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1171)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 115)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 499)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 883)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1267)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 404)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 788)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1172)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 116)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 500)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 884)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1268)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 405)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 789)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1173)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 501)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 885)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1269)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 406)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 790)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1174)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 118)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 502)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 886)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1270)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 407)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 791)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1175)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 119)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 503)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 887)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1271)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 408)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 792)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1176)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 120)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 504)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 888)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1272)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 409)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 793)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1177)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 121)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 505)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 889)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1273)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 410)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 794)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1178)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 122)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 506)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 890)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1274)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 411)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 795)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1179)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 123)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 507)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 891)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1275)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 412)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 796)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1180)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 124)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 508)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 892)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1276)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 413)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 797)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1181)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 125)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 509)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 893)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1277)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 414)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 798)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1182)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 510)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 894)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1278)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 415)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 799)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1183)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 127)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 511)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 895)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1279)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 416)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 800)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1184)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 128)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 512)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 896)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1280)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 417)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 801)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1185)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 129)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 513)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 897)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1281)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 418)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 802)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1186)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 130)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 514)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 898)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1282)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 419)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 803)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1187)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 131)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 515)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 899)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1283)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 420)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 804)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1188)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 132)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 516)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 900)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1284)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 421)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 805)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1189)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 133)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 517)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 901)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1285)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 422)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 806)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1190)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 134)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 518)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 902)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1286)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 423)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 807)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1191)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 519)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 903)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1287)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 40)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 424)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 808)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 136)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 520)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 904)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 41)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 425)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 809)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 137)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 521)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 905)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1289)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 426)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 810)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 138)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 522)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 906)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1290)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 43)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 427)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 811)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 139)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 523)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 907)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 44)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 428)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 812)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1196)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 140)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 524)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 908)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1292)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 429)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 813)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1197)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 141)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 525)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 909)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1293)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 430)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 814)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 142)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 526)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 910)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 431)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 815)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1199)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 143)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 527)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 911)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1295)]));
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 64; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x))] = (((((1 <= ((((int)threadIdx.x) / 7) + ry_outer_outer)) && (((((int)threadIdx.x) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49)) + (ry_outer_outer * 7)) + rx_outer_outer) + ((int)threadIdx.x)) - 8)] : 0 [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 49) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 34) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 19) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 53) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 38) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 23) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 57) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 22) {
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 378)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 8) + rc_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 256)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 320)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 128)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 384)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 192)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 448)]));
+ }
+ }
}
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 196)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 4)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 588)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 12)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 4)]), 0.000000e+00f);
}
}
@@ -1426,7 +585,7 @@ In the example below we resume the status and do more 5 trials.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
Get devices for measurement successfully!
-
+ .T
@@ -1434,7 +593,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 39.782 seconds)
+ **Total running time of the script:** ( 5 minutes 43.646 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 4b409a6c29..28847874f5 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)
- 7.9185 7.9233 7.9300 7.9022 0.0118
+ 7.8730 7.8724 7.8842 7.8623 0.0090
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.028 seconds)
+ **Total running time of the script:** ( 1 minutes 5.003 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 8b8f2e3238..623d123e1c 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)
- 756.7985 755.3485 759.9386 755.1084 2.2225
+ 750.2198 750.1006 750.6996 749.8592 0.3533
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 40.825 seconds)
+ **Total running time of the script:** ( 1 minutes 37.989 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 1535cefe17..f99a790e33 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
@@ -389,27 +389,74 @@ 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(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.Buffer((512,), data=compute_1)
- for i_outer_inner in range(2):
- for i_inner_init, j_init in T.grid(16, 16):
- compute_2[i_outer_inner * 256 + i_inner_init * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 32, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 16, 16):
- cse_var_1 = T.var("int32")
+ for i0_outer_i1_outer_fused in T.parallel(16):
+ compute_1 = T.allocate([4096], "float32", "global")
+ compute_2 = T.Buffer((4096,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(2, 2):
+ for i_inner_init in range(64):
+ cse_var_1: T.int32 = i_outer_inner * 2048 + 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(cse_var_2, i0_outer_i1_outer_fused * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 64):
+ cse_var_2 = T.var("int32")
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_2: T.int32 = i0_outer_i1_outer_fused % 32
- if T.likely(elem_idx < placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]):
- 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)
- cse_var_3: T.int32 = i_outer_inner * 256 + i_inner * 16 + j
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 8192 + i_outer_inner * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
- for i0_inner in range(32):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 32 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i0_outer_i1_outer_fused * 2 + nb_j_inner
+ cse_var_19: T.int32 = i_outer_inner * 16384 + i_inner * 256
+ cse_var_18: T.int32 = i_outer_inner * 2048 + 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(128, 32):
+ cse_var_22: T.int32 = i0_inner * 512 + i0_outer_i1_outer_fused * 32 + i1_inner
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 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_4:cse_var_4 + 16], T.Broadcast(T.float32(0), 16))
+ compute_3[cse_var_22] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_22], T.float32(0))
@@ -459,7 +506,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.658 ms
+ Execution time of this operator: 1.868 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 22502e874e..3795b685bd 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.125** total execution time for **how_to_tune_with_autotvm** files:
+**00:29.251** 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``) | 00:34.090 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:29.219 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 8848adbbf3..9d96bf0db1 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
@@ -268,9 +268,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 24.50/24.50 result: MeasureResult(costs=(0.009450592,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.927823066711426, timestamp=1675408284.1870978) [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7562431
- No: 2 GFLOPS: 34.11/34.11 result: MeasureResult(costs=(0.0067868779333333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.17113995552063, timestamp=1675408284.9329607) [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4723222
- No: 3 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -392,8 +390,8 @@ 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, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4850607
- No: 4 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5720156
+ No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -515,8 +513,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7076570
- No: 5 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1350091
+ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -638,8 +636,9 @@ 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, 1, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5098814
- No: 6 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1084210
+ No: 4 GFLOPS: 234.98/234.98 result: MeasureResult(costs=(0.0009851961656441718,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.86448335647583, timestamp=1675416424.5687695) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9496804
+ No: 5 GFLOPS: 0.00/234.98 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
@@ -761,162 +760,500 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9225039
- No: 7 GFLOPS: 0.00/34.11 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)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5791407
+ No: 6 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
- 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()
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 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', 0), ('unroll_explicit', 1)],None,5553495
+ No: 7 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 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: 0x00007fa80399cfa2
- 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
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1617
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
- 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, 2, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5376717
- No: 8 GFLOPS: 219.53/219.53 result: MeasureResult(costs=(0.0010545141315789473,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5045509338378906, timestamp=1675408294.3802714) [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6014886
- No: 9 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9602668
+ No: 8 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8292002
+ No: 9 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4126925
+ No: 10 GFLOPS: 0.00/234.98 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
@@ -1038,9 +1375,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1053056
- No: 10 GFLOPS: 35.97/219.53 result: MeasureResult(costs=(0.0064353880625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6258225440979004, timestamp=1675408296.2155497) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5930210
- No: 11 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3349256
+ No: 11 GFLOPS: 0.00/234.98 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
@@ -1162,8 +1498,8 @@ 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, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6627242
- No: 12 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7804937
+ No: 12 GFLOPS: 0.00/234.98 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
@@ -1285,8 +1621,8 @@ 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, 128, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9308877
- No: 13 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9989606
+ No: 13 GFLOPS: 0.00/234.98 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
@@ -1408,9 +1744,8 @@ 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4778309
- No: 14 GFLOPS: 69.09/219.53 result: MeasureResult(costs=(0.003350876866666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5380854606628418, timestamp=1675408297.966354) [('tile_f', [-1, 4, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,210046
- No: 15 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3806842
+ No: 14 GFLOPS: 0.00/234.98 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
@@ -1532,8 +1867,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4905581
- No: 16 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8008466
+ No: 15 GFLOPS: 0.00/234.98 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
@@ -1655,8 +1990,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3827802
- No: 17 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2720264
+ No: 16 GFLOPS: 0.00/234.98 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
@@ -1778,8 +2113,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1293466
- No: 18 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5863570
+ No: 17 GFLOPS: 0.00/234.98 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
@@ -1901,8 +2236,9 @@ 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, 2, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2317471
- No: 19 GFLOPS: 0.00/219.53 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, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8950972
+ No: 18 GFLOPS: 17.71/234.98 result: MeasureResult(costs=(0.013072096,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.992128849029541, timestamp=1675416431.2788076) [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1975313
+ No: 19 GFLOPS: 0.00/234.98 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
@@ -2024,8 +2360,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,369957
- No: 20 GFLOPS: 80.00/219.53 result: MeasureResult(costs=(0.002893765457142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5332930088043213, timestamp=1675408299.739333) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3714223
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6611344
+ No: 20 GFLOPS: 6.76/234.98 result: MeasureResult(costs=(0.03422482275,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7962653636932373, timestamp=1675416432.1522903) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7645625
@@ -2080,9 +2416,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6014886
+ [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9496804
Finish loading 20 records
- Time cost of this operator: 0.001487
+ Time cost of this operator: 0.001338
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 5eb4afa62b..f4d125f8ad 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 314.8 98.72 (1, 2, 10, 10, 3) 2 1 [314.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.12 0.978 (1, 6, 10, 10) 1 1 [3.12]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.301 (1, 1, 10, 10, 3) 1 1 [0.961]
- Total_time - 318.881 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.0 98.706 (1, 2, 10, 10, 3) 2 1 [310.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.108 0.99 (1, 6, 10, 10) 1 1 [3.108]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.304 (1, 1, 10, 10, 3) 1 1 [0.955]
+ Total_time - 314.063 - - - - -
@@ -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 105.7 97.568 (1, 6, 10, 10, 1) 2 1 [105.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.791 1.653 (1, 6, 10, 10) 1 1 [1.791]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.778 (1, 3, 10, 10, 1) 1 1 [0.843]
- Total_time - 108.334 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.2 98.004 (1, 6, 10, 10, 1) 2 1 [134.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.294 (1, 6, 10, 10) 1 1 [1.772]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.701 (1, 1, 10, 10, 3) 1 1 [0.96]
+ Total_time - 136.933 - - - - -
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 7b10018b2b..d6f6db8418 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, 42.6MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 233MB/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 11.778 seconds)
+ **Total running time of the script:** ( 1 minutes 8.458 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 c53203e8b6..1c901cf0ff 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/tmpf4ptv5_b/images/random'
+ '/tmp/tmpn89yh4fo/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], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [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/tmpf4ptv5_b/images/target contains 8144 images
- /tmp/tmpf4ptv5_b/images/random contains 5000 images
+ /tmp/tmpn89yh4fo/images/target contains 8144 images
+ /tmp/tmpn89yh4fo/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2188 - accuracy: 0.9242 - val_loss: 0.1065 - val_accuracy: 0.9637 - 47s/epoch - 144ms/step
+ 328/328 - 46s - loss: 0.2156 - accuracy: 0.9249 - val_loss: 0.1436 - val_accuracy: 0.9535 - 46s/epoch - 141ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0937 - accuracy: 0.9659 - val_loss: 0.1405 - val_accuracy: 0.9566 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.1009 - accuracy: 0.9637 - val_loss: 0.1320 - val_accuracy: 0.9539 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0700 - accuracy: 0.9744 - val_loss: 0.0954 - val_accuracy: 0.9721 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0731 - accuracy: 0.9712 - val_loss: 0.0958 - val_accuracy: 0.9679 - 43s/epoch - 130ms/step
- <keras.callbacks.History object at 0x7f863c47fa10>
+ <keras.callbacks.History object at 0x7ffabc510f10>
@@ -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 53.103 seconds)
+ **Total running time of the script:** ( 4 minutes 43.587 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 6b0136d063..68c7410e92 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
=================
-**07:12.503** total execution time for **how_to_work_with_microtvm** files:
+**06:56.135** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:53.103 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:43.587 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:11.778 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:08.458 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:54.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.295 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.137 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.702 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:05.367 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:05.094 | 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 55238bdff9..665d75e65f 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:45.605** total execution time for **how_to_work_with_relay** files:
+**00:43.847** 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``) | 00:33.081 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.895 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.770 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.394 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.748 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.551 | 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 |
+----------------------------------------------------------------------------------------------------+-----------+--------+
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 3fe2cad68b..295f326404 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 0x7f84e7df2170>
+ <function my_cuda_math_rule at 0x7ff95f560f80>
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 e6de9e8736..c78f51ad73 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
=================
-**00:08.831** total execution time for **how_to_work_with_schedules** files:
+**00:07.709** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.229 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.200 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.145 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.587 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.568 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.568 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.548 | 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``) | 00:00.113 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.051 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index d40290a5b1..2bd62f5a02 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -340,7 +340,7 @@ The importing needs to happen before the tensorized GEMV being executed.
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmptw2hdwu6/input0.cc'\nsource_filename = \"/tmp/tmptw2hdwu6/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca float*, [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmp2910ew2g/input0.cc'\nsource_filename = \"/tmp/tmp2910ew2g/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca float*, [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
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 aa197b5605..2d1536c889 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
=================
-**00:31.158** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:29.575** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.151 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:29.568 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index f237bf70ea..dd8ba218ad 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 33.40s!
+ resnet18_v1 inference graph built in 31.39s!
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 6f2b33b36c..4a298ddbac 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 22.59s!
+ yolov3-tiny inference graph built in 21.56s!
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 6d2864fc52..1407dcc8e6 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:40.185** total execution time for **topic_vta_tutorials_frontend** files:
+**01:36.504** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.240 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.386 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.945 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.118 | 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 d743942fa7..d74722721f 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
=================
-**00:03.213** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.163** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.741 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.711 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.473 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.452 | 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 8800b946af..c18656380b 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:
+**00:00.755** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.407 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.391 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.381 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.364 | 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 3e41b2cbd4..8c927c3828 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,6 +207,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+
+ .T
+
@@ -318,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.447 ms
+ Execution time of this operator: 98.840 ms
@@ -436,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.143 seconds)
+ **Total running time of the script:** ( 1 minutes 41.477 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 b062eb99d1..d5495cd6ea 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: 10.09/10.09 result: MeasureResult(costs=(0.026605293799999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7496817111968994, timestamp=1675406725.1395779) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
- No: 2 GFLOPS: 12.27/12.27 result: MeasureResult(costs=(0.0218823138,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5906140804290771, timestamp=1675406726.5292425) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 3 GFLOPS: 9.25/12.27 result: MeasureResult(costs=(0.0290300618,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7711708545684814, timestamp=1675406727.2573187) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
- No: 4 GFLOPS: 9.24/12.27 result: MeasureResult(costs=(0.0290646116,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6973280906677246, timestamp=1675406728.7544155) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
- No: 5 GFLOPS: 9.88/12.27 result: MeasureResult(costs=(0.0271788372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6953585147857666, timestamp=1675406729.5636196) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 6 GFLOPS: 2.75/12.27 result: MeasureResult(costs=(0.0974577844,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8022475242614746, timestamp=1675406731.3773532) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
- No: 7 GFLOPS: 2.42/12.27 result: MeasureResult(costs=(0.11076174220000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0055735111236572, timestamp=1675406734.1834998) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
- No: 8 GFLOPS: 3.06/12.27 result: MeasureResult(costs=(0.0876125186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.642512321472168, timestamp=1675406735.8364882) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
- No: 9 GFLOPS: 2.25/12.27 result: MeasureResult(costs=(0.11930834939999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1392741203308105, timestamp=1675406738.0958972) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 10 GFLOPS: 2.37/12.27 result: MeasureResult(costs=(0.113495261,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.055821657180786, timestamp=1675406740.169546) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
+ No: 1 GFLOPS: 9.61/9.61 result: MeasureResult(costs=(0.0279437706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7079107761383057, timestamp=1675414896.7156808) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+ No: 2 GFLOPS: 1.54/9.61 result: MeasureResult(costs=(0.17420288599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0246503353118896, timestamp=1675414900.4974241) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+ No: 3 GFLOPS: 10.64/10.64 result: MeasureResult(costs=(0.025226920999999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6309366226196289, timestamp=1675414901.9013178) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 4 GFLOPS: 10.83/10.83 result: MeasureResult(costs=(0.0247976122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6232948303222656, timestamp=1675414902.5543) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
+ No: 5 GFLOPS: 2.88/10.83 result: MeasureResult(costs=(0.0930837148,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7398769855499268, timestamp=1675414904.4685497) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
+ No: 6 GFLOPS: 12.82/12.82 result: MeasureResult(costs=(0.0209332462,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5863316059112549, timestamp=1675414905.0601938) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+ No: 7 GFLOPS: 14.58/14.58 result: MeasureResult(costs=(0.018415987,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.603083610534668, timestamp=1675414906.3519657) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+ No: 8 GFLOPS: 3.69/14.58 result: MeasureResult(costs=(0.0727446234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.403618335723877, timestamp=1675414907.759496) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 9 GFLOPS: 9.13/14.58 result: MeasureResult(costs=(0.029410109400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9025619029998779, timestamp=1675414908.778903) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+ No: 10 GFLOPS: 11.48/14.58 result: MeasureResult(costs=(0.023389680000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5853416919708252, timestamp=1675414909.4101672) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 8daa21b7f8..1b4e65200f 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': 519.2060856400008, 'median': 518.6517025499995, 'std': 1.923171496934491}
+ {'mean': 509.73409502000106, 'median': 509.5896542999981, 'std': 2.5278528585166624}
@@ -545,30 +545,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 21.83/ 21.83 GFLOPS | Progress: (4/20) | 8.09 s
[Task 1/25] Current/Best: 14.19/ 21.83 GFLOPS | Progress: (8/20) | 12.18 s
[Task 1/25] Current/Best: 23.32/ 23.32 GFLOPS | Progress: (12/20) | 16.37 s
[Task 1/25] Current/Best: 11.07/ 23.32 GFLOPS | Progress: (16/20) | 20.12 s
[Task 1/25] Current/Best: 11.27/ 23.32 GFLOPS | Progress: (20/20) | 23.28 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 9.24/ 17.96 GFLOPS | Progress: (4/20) | 3.36 s
[Task 2/25] Current/Best: 10.50/ 20.67 GFLOPS | Progress: (8/20) | 6.45 s
[Task 2/25] Current/Best: 14.71/ 20.67 GFLOPS | Progress: (12/20) | 7.82 s
[Task 2/25] Current/Best: 10.17/ 20.67 GFLOPS | Progress: (16/20) | 10.16 s
[Task 2/25] Current/Best: 17.93/ 20.67 GFLOPS | Progress: (20/20) | 11.91 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.99/ 14.99 GFLOPS | Progress: (4/20) | 4.05 s
[Task 3/25] Current/Best: 10.61/ 19.50 GFLOPS | Progress: (8/20) | 6.45 s
[Task 3/25] Current/Best: 11.32/ 19.50 GFLOPS | Progress: (12/20) | 8.76 s
[Task 3/25] Current/Best: 14.24/ 19.50 GFLOPS | Progress: (16/20) | 11.28 s
[Task 3/25] Current/Best: 11.03/ 22.49 GFLOPS | Progress: (20/20) | 15.02 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (4/20) | 4.15 s
[Task 4/25] Current/Best: 10.85/ 19.99 GFLOPS | Progress: (8/20) | 6.72 s
[Task 4/25] Current/Best: 15.28/ 19.99 GFLOPS | Progress: (12/20) | 8.48 s
[Task 4/25] Current/Best: 13.12/ 20.71 GFLOPS | Progress: (16/20) | 13.14 s
[Task 4/25] Current/Best: 9.64/ 20.71 GFLOPS | Progress: (20/20) | 24.42 s
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 5/25] Current/Best: 10.01/ 15.61 GFLOPS | Progress: (4/20) | 4.43 s
[Task 5/25] Current/Best: 17.70/ 18.54 GFLOPS | Progress: (8/20) | 6.14 s
[Task 5/25] Current/Best: 10.19/ 21.62 GFLOPS | Progress: (12/20) | 8.19 s
[Task 5/25] Current/Best: 5.70/ 21.62 GFLOPS | Progress: (16/20) | 11.00 s
[Task 5/25] Current/Best: 5.58/ 21.62 GFLOPS | Progress: (20/20) | 13.78 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.45/ 18.43 GFLOPS | Progress: (4/20) | 4.60 s
[Task 6/25] Current/Best: 11.72/ 18.43 GFLOPS | Progress: (8/20) | 8.38 s
[Task 6/25] Current/Best: 17.74/ 18.43 GFLOPS | Progress: (12/20) | 12.18 s
[Task 6/25] Current/Best: 13.49/ 18.43 GFLOPS | Progress: (16/20) | 15.17 s
[Task 6/25] Current/Best: 13.99/ 18.43 GFLOPS | Progress: (20/20) | 18.66 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.38/ 20.94 GFLOPS | Progress: (4/20) | 3.94 s
[Task 7/25] Current/Best: 6.03/ 20.94 GFLOPS | Progress: (8/20) | 6.97 s
[Task 7/25] Current/Best: 10.33/ 20.94 GFLOPS | Progress: (12/20) | 9.47 s
[Task 7/25] Current/Best: 11.34/ 20.94 GFLOPS | Progress: (16/20) | 11.97 s
[Task 7/25] Current/Best: 6.16/ 20.94 GFLOPS | Progress: (20/20) | 14.46 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 3.60/ 13.72 GFLOPS | Progress: (4/20) | 13.73 s
[Task 8/25] Current/Best: 12.34/ 13.72 GFLOPS | Progress: (8/20) | 19.50 s
[Task 8/25] Current/Best: 6.54/ 18.55 GFLOPS | Progress: (12/20) | 23.08 s
[Task 8/25] Current/Best: 7.56/ 18.55 GFLOPS | Progress: (16/20) | 27.63 s
[Task 8/25] Current/Best: 12.71/ 18.55 GFLOPS | Progress: (20/20) | 30.19 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 16.01/ 17.20 GFLOPS | Progress: (4/20) | 3.63 s
[Task 9/25] Current/Best: 13.13/ 21.97 GFLOPS | Progress: (8/20) | 9.87 s
[Task 9/25] Current/Best: 10.43/ 21.97 GFLOPS | Progress: (12/20) | 12.35 s
[Task 9/25] Current/Best: 15.89/ 22.27 GFLOPS | Progress: (16/20) | 17.55 s
[Task 9/25] Current/Best: 14.44/ 22.27 GFLOPS | Progress: (20/
20) | 20.32 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 5.98/ 10.79 GFLOPS | Progress: (4/20) | 4.82 s
[Task 10/25] Current/Best: 11.28/ 19.12 GFLOPS | Progress: (8/20) | 6.97 s
[Task 10/25] Current/Best: 15.78/ 19.12 GFLOPS | Progress: (12/20) | 9.07 s
[Task 10/25] Current/Best: 3.04/ 19.12 GFLOPS | Progress: (16/20) | 13.15 s
[Task 10/25] Current/Best: 13.49/ 19.12 GFLOPS | Progress: (20/20) | 16.17 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 3.11/ 17.30 GFLOPS | Progress: (4/20) | 4.99 s
[Task 11/25] Current/Best: 8.86/ 17.30 GFLOPS | Progress: (8/20) | 7.89 s
[Task 11/25] Current/Best: 7.72/ 17.30 GFLOPS | Progress: (12/20) | 10.42 s
[Task 11/25] Current/Best: 6.18/ 17.30 GFLOPS | Progress: (16/20) | 13.74 s
[Task 11/25] Current/Best: 14.32/ 17.30 GFLOPS | Progress: (20/20) | 16.50 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.29/ 19.30 GFLOPS | Progress: (4/20) | 4.89 s
[Task 12/25] Current/Best: 15.00/ 19.30 GFLOPS | Progress: (8/20) | 7.61 s
[Task 12/25] Current/Best: 10.54/ 19.30 GFLOPS | Progress: (12/20) | 9.94 s
[Task 12/25] Current/Best: 13.17/ 19.30 GFLOPS | Progress: (16/20) | 16.54 s
[Task 12/25] Current/Best: 9.13/ 19.30 GFLOPS | Progress: (20/20) | 18.78 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 13.09/ 17.32 GFLOPS | Progress: (4/20) | 4.51 s
[Task 13/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (8/20) | 6.65 s
[Task 13/25] Current/Best: 13.18/ 22.37 GFLOPS | Progress: (12/20) | 9.98 s
[Task 13/25] Current/Best: 18.27/ 22.37 GFLOPS | Progress: (16/20) | 13.17 s
[Task 13/25] Current/Best: 17.71/ 22.37 GFLOPS | Progress: (20/20) | 17.14 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (4/20) | 3.36 s
[Task 14/25] Current/Best: 12.19/ 19.58 GFLOPS | Progress: (8/20) | 5.43 s
[Task 14/25] Current/Best: 8.92/ 19.58 GFLOPS | Progress: (12/20) | 11.47 s Done.
-
[Task 14/25] Current/Best: 14.94/ 19.58 GFLOPS | Progress: (16/20) | 13.58 s
[Task 14/25] Current/Best: 14.17/ 19.58 GFLOPS | Progress: (20/20) | 16.59 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.15/ 19.02 GFLOPS | Progress: (4/20) | 4.87 s
[Task 15/25] Current/Best: 11.52/ 20.25 GFLOPS | Progress: (8/20) | 8.71 s
[Task 15/25] Current/Best: 11.35/ 20.25 GFLOPS | Progress: (12/20) | 13.44 s
[Task 15/25] Current/Best: 12.79/ 20.33 GFLOPS | Progress: (16/20) | 15.03 s
[Task 15/25] Current/Best: 15.04/ 20.33 GFLOPS | Progress: (20/20) | 16.81 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 11.64/ 12.90 GFLOPS | Progress: (4/20) | 4.85 s
[Task 16/25] Current/Best: 6.17/ 17.72 GFLOPS | Progress: (8/20) | 7.27 s
[Task 16/25] Current/Best: 19.74/ 19.74 GFLOPS | Progress: (12/20
) | 9.18 s
[Task 16/25] Current/Best: 10.38/ 19.74 GFLOPS | Progress: (16/20) | 11.94 s
[Task 16/25] Current/Best: 18.09/ 20.47 GFLOPS | Progress: (20/20) | 13.64 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 6.43/ 10.21 GFLOPS | Progress: (4/20) | 4.87 s
[Task 17/25] Current/Best: 9.83/ 18.36 GFLOPS | Progress: (8/20) | 6.96 s
[Task 17/25] Current/Best: 23.11/ 23.11 GFLOPS | Progress: (12/20) | 9.37 s
[Task 17/25] Current/Best: 13.48/ 23.11 GFLOPS | Progress: (16/20) | 11.94 s
[Task 17/25] Current/Best: 11.17/ 23.11 GFLOPS | Progress: (20/20) | 15.08 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 15.64/ 15.64 GFLOPS | Progress: (4/20) | 4.08 s
[Task 18/25] Current/Best: 11.89/ 17.35 GFLOPS | Progress: (8/20) | 8.37 s
[Task 18/25] Current/Best: 20.78/ 20.78 GFLOPS | Progress: (12/20) | 11.85 s
[Task 18/25] Current/Best: 19.03/ 20.78 GFLOPS | Progress: (16/20) | 14.04 s
[Task 18/25] Current/Best: 11.10/ 20.78 GFLOPS | Progress: (20/20) | 17.28 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 2.69/ 21.25 GFLOPS | Progress: (4/20) | 6.03 s
[Task 19/25] Current/Best: 18.04/ 21.25 GFLOPS | Progress: (8/20) | 11.58 s
[Task 19/25] Current/Best: 19.84/ 21.25 GFLOPS | Progress: (12/20) | 15.77 s
[Task 19/25] Current/Best: 10.72/ 21.25 GFLOPS | Progress: (16/20) | 18.58 s
[Task 19/25] Current/Best: 17.82/ 21.25 GFLOPS | Progress: (20/20) | 20.84 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.30/ 11.99 GFLOPS | Progress: (4/20) | 5.97 s
[Task 20/25] Current/Best: 11.44/ 13.73 GFLOPS | Progress: (8/20) | 9.61 s
[Task 20/25] Current/Best: 16.61/ 16.61 GFLOPS | Progress: (12/20) | 12.94 s
[Task 20/25] Current/Best: 17.24/ 17.24 GFLOPS | Progress: (16/20) | 15.95 s
[Task 20/25] Current/Best: 4.14/ 17.24 GFLOPS | Progress: (20/20) | 19.36 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 12.74/ 18.26 GFLOPS | Progress: (4/20) | 3.37 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.63/ 12.63 GFLOPS | Progress: (4/20) | 11.79 s
[Task 1/25] Current/Best: 9.71/ 17.75 GFLOPS | Progress: (8/20) | 15.03 s
[Task 1/25] Current/Best: 14.18/ 18.34 GFLOPS | Progress: (12/20) | 17.67 s
[Task 1/25] Current/Best: 9.97/ 18.34 GFLOPS | Progress: (16/20) | 19.90 s
[Task 1/25] Current/Best: 22.63/ 23.91 GFLOPS | Progress: (20/20) | 22.99 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 17.19/ 21.14 GFLOPS | Progress: (4/20) | 3.05 s
[Task 2/25] Current/Best: 10.06/ 21.14 GFLOPS | Progress: (8/20) | 6.18 s
[Task 2/25] Current/Best: 7.61/ 21.14 GFLOPS | Progress: (12/20) | 7.52 s
[Task 2/25] Current/Best: 12.94/ 21.14 GFLOPS | Progress: (16/20) | 9.33 s
[Task 2/25] Current/Best: 2.03/ 21.14 GFLOPS | Progress: (20/20) | 10.79 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 13.51/ 14.49 GFLOPS | Progress: (4/20) | 4.25 s
[Task 3/25] Current/Best: 15.22/ 20.38 GFLOPS | Progress: (8/20) | 6.79 s
[Task 3/25] Current/Best: 10.70/ 20.38 GFLOPS | Progress: (12/20) | 9.16 s
[Task 3/25] Current/Best: 5.68/ 20.38 GFLOPS | Progress: (16/20) | 12.03 s
[Task 3/25] Current/Best: 16.17/ 20.38 GFLOPS | Progress: (20/20) | 14.04 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.19/ 18.89 GFLOPS | Progress: (4/20) | 4.01 s
[Task 4/25] Current/Best: 11.90/ 18.89 GFLOPS | Progress: (8/20) | 6.02 s
[Task 4/25] Current/Best: 6.52/ 18.89 GFLOPS | Progress: (12/20) | 8.25 s
[Task 4/25] Current/Best: 13.88/ 18.89 GFLOPS | Progress: (16/20) | 11.17 s
[Task 4/25] Current/Best: 18.04/ 18.89 GFLOPS | Progress: (20/20) | 13.07 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 12.43/ 17.18 GFLOPS | Progress: (4/20) | 3.84 s
[Task 5/25] Current/Best: 3.07/ 17.18 GFLOPS | Progress: (8/20) | 5.79 s
[Task 5/25] Current/Best: 14.08/ 17.18 GFLOPS | Progress: (12/20) | 8.38 s
[Task 5/25] Current/Best: 9.13/ 17.18 GFLOPS | Progress: (16/20) | 11.83 s
[Task 5/25] Current/Best: 4.75/ 17.18 GFLOPS | Progress: (20/20) | 13.99 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 16.23/ 16.23 GFLOPS | Progress: (4/20) | 5.34 s
[Task 6/25] Current/Best: 10.73/ 16.28 GFLOPS | Progress: (8/20) | 7.86 s
[Task 6/25] Current/Best: 12.96/ 16.28 GFLOPS | Progress: (12/20) | 10.85 s
[Task 6/25] Current/Best: 6.28/ 16.28 GFLOPS | Progress: (16/20) | 13.99 s
[Task 6/25] Current/Best: 15.86/ 16.28 GFLOPS | Progress: (20/20) | 16.73 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.63/ 16.49 GFLOPS | Progress: (4/20) | 4.14 s
[Task 7/25] Current/Best: 13.42/ 19.09 GFLOPS | Progress: (8/20) | 7.07 s
[Task 7/25] Current/Best: 11.87/ 19.09 GFLOPS | Progress: (12/20) | 10.02 s
[Task 7/25] Current/Best: 5.54/ 19.09 GFLOPS | Progress: (16/20) | 13.37 s
[Task 7/25] Current/Best: 10.90/ 19.09 GFLOPS | Progress: (20/20) | 15.65 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.26/ 13.92 GFLOPS | Progress: (4/20) | 6.61 s
[Task 8/25] Current/Best: 11.88/ 17.97 GFLOPS | Progress: (8/20) | 12.69 s
[Task 8/25] Current/Best: 14.97/ 17.97 GFLOPS | Progress: (12/20) | 14.79 s
[Task 8/25] Current/Best: 13.56/ 20.11 GFLOPS | Progress: (16/20) | 18.20 s
[Task 8/25] Current/Best: 9.44/ 20.11 GFLOPS | Progress: (20/20) | 21.82 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (4/20) | 3.46 s
[Task 9/25] Current/Best: 9.05/ 22.19 GFLOPS | Progress: (8/20) | 11.84 s
[Task 9/25] Current/Best: 12.28/ 22.19 GFLOPS | Progress: (12/20) | 23.00 s
[Task 9/25] Current/Best: 14.96/ 22.19 GFLOPS | Progress: (16/20) | 28.60 s
[Task 9/25] Current/Best: 6.13/ 22.19 GFLOPS | Progress: (20/20) | 37.59 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.75/ 13.00 GFLOPS | Progress: (4/20) | 4.30 s
[Task 10/25] Current/Best: 3.14/ 16.12 GFLOPS | Progress: (8/20) | 6.24 s
[Task 10/25] Current/Best: 6.51/ 16.12 GFLOPS | Progress: (12/20) | 8.20 s
[Task 10/25] Current/Best: 9.27/ 16.12 GFLOPS | Progress: (16/20) | 10.17 s
[Task 10/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (20/20
) | 12.76 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 19.39/ 19.39 GFLOPS | Progress: (4/20) | 4.49 s
[Task 11/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (8/20) | 6.74 s
[Task 11/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (12/20) | 8.93 s
[Task 11/25] Current/Best: 17.86/ 21.35 GFLOPS | Progress: (16/20) | 11.68 s
[Task 11/25] Current/Best: 18.45/ 21.35 GFLOPS | Progress: (20/20) | 14.38 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 8.30/ 15.54 GFLOPS | Progress: (4/20) | 4.35 s
[Task 12/25] Current/Best: 5.39/ 15.54 GFLOPS | Progress: (8/20) | 6.98 s
[Task 12/25] Current/Best: 3.54/ 15.54 GFLOPS | Progress: (12/20) | 11.09 s
[Task 12/25] Current/Best: 6.49/ 15.72 GFLOPS | Progress: (16/20) | 13.79 s
[Task 12/25] Current/Best: 18.93/ 20.65 GFLOPS | Progress: (20/20) | 15.79 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.21/ 13.88 GFLOPS | Progress: (4/20) | 5.10 s
[Task 13/25] Current/Best: 9.14/ 22.97 GFLOPS | Progress: (8/20) | 7.77 s
[Task 13/25] Current/Best: 11.50/ 22.97 GFLOPS | Progress: (12/20) | 11.83 s
[Task 13/25] Current/Best: 11.39/ 22.97 GFLOPS | Progress: (16/20) | 15.69 s
[Task 13/25] Current/Best: 15.05/ 22.97 GFLOPS | Progress: (20/20) | 18.03 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.05/ 21.91 GFLOPS | Progress: (4/20) | 5.09 s
[Task 14/25] Current/Best: 9.87/ 21.91 GFLOPS | Progress: (8/20) | 10.46 s
[Task 14/25] Current/Best: 12.71/ 21.91 GFLOPS | Progress: (12/20) | 13.38 s
[Task 14/25] Current/Best: 12.01/ 21.91 GFLOPS | Progress: (16/20) | 17.36 s
[Task 14/25] Current/Best: 18.37/ 21.91 GFLOPS | Progress: (20/20) | 20.60 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.47/ 13.47 GFLOPS | Progress: (4/20) | 3.60 s Done.
Done.
+
[Task 15/25] Current/Best: 18.42/ 23.18 GFLOPS | Progress: (8/20) | 5.83 s
[Task 15/25] Current/Best: 8.69/ 23.18 GFLOPS | Progress: (12/20) | 10.67 s
[Task 15/25] Current/Best: 14.59/ 23.18 GFLOPS | Progress: (16/20) | 14.04 s
[Task 15/25] Current/Best: 8.47/ 23.18 GFLOPS | Progress: (20/20) | 16.62 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.01/ 18.58 GFLOPS | Progress: (4/20) | 3.98 s
[Task 16/25] Current/Best: 9.17/ 18.58 GFLOPS | Progress: (8/20) | 5.56 s
[Task 16/25] Current/Best: 14.91/ 18.58 GFLOPS | Progress: (12/20) | 9.35 s
[Task 16/25] Current/Best: 18.96/ 21.44 GFLOPS | Progress: (16/20) | 10.78 s
[Task 16/25] Current/Best: 14.62/ 21.44 GFLOPS | Progress: (20/20) | 12.64 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 10.56/ 18.60 GFLOPS | Progress: (4/20) | 4.75 s
[Task 17/25] Current/Best: 16.93/ 21.69 GFLOPS | Progress: (8/20) | 7.21 s
[Task 17/25] Current/Best: 7.66/ 21.69 GFLOPS | Progress: (12/20) | 11.43 s
[Task 17/25] Current/Best: 16.07/ 21.69 GFLOPS | Progress: (16/20) | 14.78 s
[Task 17/25] Current/Best: 17.13/ 21.69 GFLOPS | Progress: (20/20) | 17.23 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 12.24/ 20.38 GFLOPS | Progress: (4/20) | 3.88 s
[Task 18/25] Current/Best: 14.27/ 20.38 GFLOPS | Progress: (8/20) | 5.99 s
[Task 18/25] Current/Best: 15.07/ 20.38 GFLOPS | Progress: (12/20) | 8.11 s
[Task 18/25] Current/Best: 14.21/ 20.38 GFLOPS | Progress: (16/20) | 10.55 s
[Task 18/25] Current/Best: 10.25/ 20.38 GFLOPS | Progress: (20/20) | 12.76 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 5.36/ 11.43 GFLOPS | Progress: (4/20) | 4.76 s
[Task 19/25] Current/Best: 6.18/ 19.37 GFLOPS | Progress: (8/20) | 7.30 s
[Task 19/25] Current/Best: 3.09/ 22.65 GFLOPS | Progress: (12/20) | 11.21 s
[Task 19/25] Current/Best: 9.21/ 22.65 GFLOPS | Progress: (16/20) | 13.89 s
[Task 19/25] Current/Best: 6.19/ 22.65 GFLOPS | Progress: (20/20) | 17.67 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 12.89/ 16.18 GFLOPS | Progress: (4/20) | 4.78 s
[Task 20/25] Current/Best: 10.44/ 18.50 GFLOPS | Progress: (8/20) | 8.70 s
[Task 20/25] Current/Best: 17.73/ 18.50 GFLOPS | Progress: (12/20) | 11.36 s
[Task 20/25] Current/Best: 8.05/ 18.50 GFLOPS | Progress: (16/20) | 13.81 s
[Task 20/25] Current/Best: 7.56/ 19.47 GFLOPS | Progress: (20/20) | 15.90 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 8.84/ 17.03 GFLOPS | Progress: (4/20) | 5.83 s
[Task 21/25] Current/Best: 1.62/ 17.03 GFLOPS | Progress: (8/20) | 7.93 s
[Task 21/25] Current/Best: 3.10/ 17.03 GFLOPS | Progress: (12/20) | 10.16 s
[Task 21/25] Current/Best: 12.97/ 17.03 GFLOPS | Progress: (16/20) | 13.26 s Done.
Done.
-
[Task 21/25] Current/Best: 14.41/ 18.26 GFLOPS | Progress: (8/20) | 5.76 s
[Task 21/25] Current/Best: 8.72/ 21.18 GFLOPS | Progress: (12/20) | 8.16 s
[Task 21/25] Current/Best: 12.01/ 21.18 GFLOPS | Progress: (16/20) | 9.87 s
[Task 21/25] Current/Best: 10.87/ 21.18 GFLOPS | Progress: (20/20) | 11.85 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 11.67/ 15.74 GFLOPS | Progress: (4/20) | 4.49 s
[Task 22/25] Current/Best: 17.24/ 18.12 GFLOPS | Progress: (8/20) | 6.47 s
[Task 22/25] Current/Best: 5.48/ 18.12 GFLOPS | Progress: (12/20) | 8.88 s
[Task 22/25] Current/Best: 23.04/ 23.04 GFLOPS | Progress: (16/20) | 10.45 s
[Task 22/25] Current/Best: 16.23/ 23.04 GFLOPS | Progress: (20/20) | 12.29 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 11.26/ 19.49 GFLOPS | Progress: (4/20) | 7.53 s
[Task 23/25] Current/Best: 1.55/ 19.49 GFLOPS | Progress: (8/20) | 12.92 s
[Task 23/25] Current/Best: 10.68/ 19.49 GFLOPS | Progress: (12/20) | 15.77 s
[Task 23/25] Current/Best: 11.95/ 19.49 GFLOPS | Progress: (16/20) | 17.96 s
[Task 23/25] Current/Best: 5.02/ 19.49 GFLOPS | Progress: (20/20) | 23.51 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.36/ 6.36 GFLOPS | Progress: (4/20) | 4.60 s
[Task 24/25] Current/Best: 1.97/ 6.36 GFLOPS | Progress: (8/20) | 15.57 s
[Task 24/25] Current/Best: 7.79/ 7.79 GFLOPS | Progress: (12/20) | 27.21 s
[Task 24/25] Current/Best: 0.94/ 8.81 GFLOPS | Progress: (16/20) | 38.18 s
[Task 24/25] Current/Best: 3.53/ 9.30 GFLOPS | Progress: (20/20) | 49.13 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 2.98/ 7.61 GFLOPS | Progress: (4/20) | 5.67 s
[Task 25/25] Current/Best: 1.51/ 7.61 GFLOPS | Progress: (8/20) | 16.66 s
[Task 25/25] Current/Best: 3.62/ 9.09 GFLOPS | Progress: (12/20) | 28.72 s
[Task 25/25] Current/Best: 8.64/ 9.09 GFLOPS | Progress: (16/20) | 39.65 s
[Task 25/25] Current/Best: 7.23/ 9.28 GFLOPS | Progress: (20/20) | 50.58 s
+
[Task 21/25] Current/Best: 17.97/ 17.97 GFLOPS | Progress: (20/20) | 15.06 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 23.04/ 23.04 GFLOPS | Progress: (4/20) | 4.16 s
[Task 22/25] Current/Best: 5.21/ 23.04 GFLOPS | Progress: (8/20) | 6.54 s
[Task 22/25] Current/Best: 11.35/ 23.04 GFLOPS | Progress: (12/20) | 8.39 s
[Task 22/25] Current/Best: 4.81/ 23.04 GFLOPS | Progress: (16/20) | 10.69 s
[Task 22/25] Current/Best: 19.83/ 23.04 GFLOPS | Progress: (20/20) | 12.41 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 12.47/ 23.18 GFLOPS | Progress: (4/20) | 6.92 s
[Task 23/25] Current/Best: 8.20/ 23.18 GFLOPS | Progress: (8/20) | 10.47 s
[Task 23/25] Current/Best: 10.95/ 23.18 GFLOPS | Progress: (12/20) | 13.40 s
[Task 23/25] Current/Best: 23.30/ 23.30 GFLOPS | Progress: (16/20) | 15.86 s
[Task 23/25] Current/Best: 12.36/ 23.30 GFLOPS | Progress: (20/20) | 18.91 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.58/ 9.86 GFLOPS | Progress: (4/20) | 3.99 s
[Task 24/25] Current/Best: 3.67/ 9.86 GFLOPS | Progress: (8/20) | 14.65 s
[Task 24/25] Current/Best: 2.33/ 10.74 GFLOPS | Progress: (12/20) | 26.43 s
[Task 24/25] Current/Best: 1.55/ 10.74 GFLOPS | Progress: (16/20) | 37.91 s
[Task 24/25] Current/Best: 2.33/ 10.74 GFLOPS | Progress: (20/20) | 50.00 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 3.02/ 8.71 GFLOPS | Progress: (4/20) | 12.44 s
[Task 25/25] Current/Best: 8.69/ 8.71 GFLOPS | Progress: (8/20) | 24.22 s
[Task 25/25] Current/Best: 1.55/ 8.71 GFLOPS | Progress: (12/20) | 35.16 s
[Task 25/25] Current/Best: 8.07/ 9.31 GFLOPS | Progress: (16/20) | 46.08 s
[Task 25/25] Current/Best: 4.47/ 9.31 GFLOPS | Progress: (20/20) | 57.58 s
@@ -722,8 +722,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 422.1551961599971, 'median': 422.1609129499939, 'std': 1.4842894634763848}
- unoptimized: {'mean': 519.2060856400008, 'median': 518.6517025499995, 'std': 1.923171496934491}
+ optimized: {'mean': 417.8435154399949, 'median': 417.04131054999607, 'std': 2.5236392821839067}
+ unoptimized: {'mean': 509.73409502000106, 'median': 509.5896542999981, 'std': 2.5278528585166624}
@@ -746,7 +746,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 16.205 seconds)
+ **Total running time of the script:** ( 11 minutes 57.068 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 1f47ae99be..f21653a732 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
- 1.238e-07 secs/op
+ 1.35e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 33d11b407a..12602c0734 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -277,7 +277,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x12970fe0)), stage(b, placeholder(b, 0x22bbd970)), 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, 0x226ad3d0)), stage(b, placeholder(b, 0x9b9dc40)), 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 a3d97664f9..8e6fb51e07 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
=================
-**15:34.008** total execution time for **tutorial** files:
+**15:32.925** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:16.205 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:57.068 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:18.143 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:41.477 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.057 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.348 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.091 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:20.017 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:17.580 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.484 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.467 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.838 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.822 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.174 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.158 | 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 2efdac6fee..60706bb664 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -504,10 +504,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.13895999979286e-06 1.0
- naive 6.668599999999999e-06 0.9341136524358578
- parallel 7.3086e-06 1.0237625648850899
- vector 2.46032e-05 3.446328316829604
+ numpy 7.248970000546251e-06 1.0
+ naive 6.642e-06 0.9162681042271507
+ parallel 7.063099999999999e-06 0.9743591157733795
+ vector 2.4587000000000004e-05 3.3917922129829803
@@ -928,7 +928,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018986
+ Numpy running time: 0.017485
@@ -986,7 +986,7 @@ optimizations.
.. code-block:: none
- none: 3.392148
+ none: 3.306402
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.309954
+ blocking: 0.293836
@@ -1170,7 +1170,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.346129
+ vectorization: 0.333988
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1236,7 +1236,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116968
+ loop permutation: 0.113655
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1327,7 +1327,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.107733
+ array packing: 0.109073
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1410,7 +1410,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110402
+ block caching: 0.110776
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1484,7 +1484,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146132
+ parallelization: 0.146266
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1554,13 +1554,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3921479667 1.0
- blocking 0.3099542307 0.09137403018463676
- vectorization 0.34612859 0.10203817563321861
- loop permutation 0.11696775210000002 0.034481913303384085
- array packing 0.1077331579 0.03175956914544815
- block caching 0.1104019172 0.03254631527981453
- parallelization 0.1461321517 0.04307953342087328
+ none 3.3064016510000003 1.0
+ blocking 0.2938362989 0.08886890641708066
+ vectorization 0.3339881545 0.10101257794829234
+ loop permutation 0.1136548737 0.034374188527768794
+ array packing 0.1090731691 0.03298848131986975
+ block caching 0.11077565 0.033503385762735934
+ parallelization 0.14626609029999998 0.04423724209542502
@@ -1600,11 +1600,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.057 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 4a67e162fb..5ca7db306f 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-d35a8ab1353afc40317396b2ddfda8f35a99ba8a
+209f074e96a654bd1830de1c769ee3d7c4c01bd2
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index fdded24e21..eba946c9f4 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.041 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.700 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 0c9b4b3a32..09bd4103ee 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ 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 976ms/step
+1/1 [==============================] - 1s 947ms/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 bdbca07ebd..aaed88627e 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
<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.zipdf0b6226-bfb2-416d-b47d-d24a74034118 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.zip4def1531-ec12-4f36-b69c-49a5180c35ec 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 9d4fa09bd4..40b156177c 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,13 +449,13 @@ 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]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 51.3MB/s]
- 27%|##7 | 11.2M/41.5M [00:00<00:00, 50.1MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 35.1MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 46.9MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 52.8MB/s]
- 96%|#########6| 40.0M/41.5M [00:00<00:00, 51.7MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 49.8MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 39.9MB/s]
+ 24%|##4 | 10.1M/41.5M [00:00<00:01, 26.4MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:01, 26.2MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 25.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:01<00:00, 19.0MB/s]
+ 96%|#########6| 40.0M/41.5M [00:01<00:00, 25.0MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 25.4MB/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 ad75d2e920..319a325912 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,12 +432,13 @@ 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]
- 19%|#9 | 8.55M/44.7M [00:00<00:00, 89.6MB/s]
- 38%|###8 | 17.1M/44.7M [00:00<00:00, 85.2MB/s]
- 58%|#####8 | 26.1M/44.7M [00:00<00:00, 83.7MB/s]
- 78%|#######7 | 34.7M/44.7M [00:00<00:00, 86.1MB/s]
- 96%|#########6| 42.9M/44.7M [00:00<00:00, 83.4MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 78.3MB/s]
+ 14%|#4 | 6.30M/44.7M [00:00<00:00, 46.7MB/s]
+ 24%|##4 | 10.8M/44.7M [00:00<00:01, 30.8MB/s]
+ 48%|####7 | 21.4M/44.7M [00:00<00:00, 56.7MB/s]
+ 65%|######5 | 29.2M/44.7M [00:00<00:00, 62.9MB/s]
+ 81%|######## | 36.0M/44.7M [00:00<00:00, 46.0MB/s]
+ 93%|#########2| 41.4M/44.7M [00:00<00:00, 46.9MB/s]
+100%|##########| 44.7M/44.7M [00:01<00:00, 46.7MB/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 df5933f6cf..1a965409ee 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ 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 24.705 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.828 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 9ccce7f141..0f8e0e5e94 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:33.801</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:24.226</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:24.705</p></td>
+<td><p>01:21.828</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>01:19.041</p></td>
+<td><p>01:16.700</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>00:53.630</p></td>
+<td><p>00:52.403</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>00:36.700</p></td>
+<td><p>00:36.379</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>00:31.730</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:30.540</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>00:31.260</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
+<td><p>00:30.202</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>00:27.736</p></td>
+<td><p>00:27.236</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>00:24.899</p></td>
+<td><p>00:24.967</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>00:21.410</p></td>
+<td><p>00:21.362</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>00:02.690</p></td>
+<td><p>00:02.608</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 83be913ed5..6671dd6196 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2689.0542 2688.5836 2693.3420 2687.1370 1.6496
+ 2682.1442 2681.3672 2686.9123 2680.1429 2.2582
</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 072b47d966..a51d4b0f21 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.7706 16.8533 17.1930 16.0958 0.3462
+ 15.5065 15.4865 15.6432 15.4388 0.0652
</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 cd90f9e04a..1f8771fbc3 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,28 +454,32 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 5%|4 | 7.89M/170M [00:00<00:02, 82.7MB/s]
- 9%|9 | 15.8M/170M [00:00<00:02, 67.7MB/s]
- 13%|#3 | 22.4M/170M [00:00<00:03, 49.9MB/s]
- 16%|#6 | 27.6M/170M [00:00<00:03, 44.6MB/s]
- 21%|## | 35.2M/170M [00:00<00:02, 54.2MB/s]
- 25%|##4 | 42.1M/170M [00:00<00:02, 50.4MB/s]
- 29%|##8 | 49.0M/170M [00:00<00:02, 56.0MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 57.2MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 63.1MB/s]
- 44%|####3 | 74.1M/170M [00:01<00:01, 73.4MB/s]
- 48%|####7 | 81.3M/170M [00:01<00:01, 65.5MB/s]
- 52%|#####2 | 88.5M/170M [00:01<00:01, 68.0MB/s]
- 57%|#####6 | 96.0M/170M [00:01<00:01, 62.3MB/s]
- 61%|######1 | 104M/170M [00:01<00:01, 65.5MB/s]
- 66%|######6 | 113M/170M [00:01<00:00, 70.1MB/s]
- 74%|#######4 | 126M/170M [00:02<00:00, 89.0MB/s]
- 80%|######## | 136M/170M [00:02<00:00, 74.1MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 72.4MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 74.1MB/s]
- 94%|#########4| 160M/170M [00:02<00:00, 71.3MB/s]
- 98%|#########8| 167M/170M [00:02<00:00, 67.3MB/s]
-100%|##########| 170M/170M [00:02<00:00, 64.3MB/s]
+ 4%|3 | 6.30M/170M [00:00<00:04, 42.6MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:03, 52.8MB/s]
+ 12%|#1 | 19.6M/170M [00:00<00:02, 53.8MB/s]
+ 15%|#4 | 24.8M/170M [00:00<00:03, 47.0MB/s]
+ 18%|#7 | 30.3M/170M [00:00<00:02, 49.8MB/s]
+ 21%|## | 35.2M/170M [00:00<00:03, 43.8MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:03, 42.6MB/s]
+ 27%|##7 | 46.2M/170M [00:01<00:02, 48.5MB/s]
+ 31%|###1 | 53.2M/170M [00:01<00:02, 54.9MB/s]
+ 35%|###4 | 58.6M/170M [00:01<00:02, 50.2MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:02, 48.9MB/s]
+ 43%|####3 | 73.2M/170M [00:01<00:01, 61.5MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 62.6MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 60.0MB/s]
+ 57%|#####6 | 96.0M/170M [00:01<00:01, 56.2MB/s]
+ 61%|######1 | 104M/170M [00:02<00:01, 53.0MB/s]
+ 66%|######5 | 112M/170M [00:02<00:01, 54.5MB/s]
+ 71%|####### | 120M/170M [00:02<00:00, 60.7MB/s]
+ 75%|#######5 | 128M/170M [00:02<00:00, 58.2MB/s]
+ 79%|#######8 | 134M/170M [00:02<00:00, 53.6MB/s]
+ 82%|########1 | 139M/170M [00:02<00:00, 53.9MB/s]
+ 85%|########5 | 144M/170M [00:02<00:00, 54.7MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 59.2MB/s]
+ 95%|#########4| 161M/170M [00:03<00:00, 68.1MB/s]
+ 99%|#########8| 168M/170M [00:03<00:00, 66.2MB/s]
+100%|##########| 170M/170M [00:03<00:00, 56.1MB/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=& [...]
@@ -573,7 +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 34.346 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.248 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 d66fdc6560..6c89234b87 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,9 +495,9 @@ 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, 46.0MB/s]
- 91%|#########1| 12.4M/13.6M [00:00<00:00, 45.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 49.1MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 50.2MB/s]
+ 94%|#########4| 12.8M/13.6M [00:00<00:00, 49.8MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 52.1MB/s]
</pre></div>
</div>
</div>
@@ -588,7 +588,7 @@ 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)
- 90.2701 90.2320 91.1414 90.1097 0.1864
+ 90.1649 89.9985 94.8026 89.8245 0.6398
</pre></div>
</div>
<div class="admonition note">
@@ -627,7 +627,7 @@ 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 15.782 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.337 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 7694e7df7e..04e57f48df 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -580,7 +580,7 @@ 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)
- 119.3250 119.3362 119.9164 118.5386 0.3018
+ 116.5960 116.3894 121.0563 115.7927 0.6959
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ 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 34.085 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.389 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 3716c529dd..98bf651945 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ 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 47.374 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.073 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 843b6b4b6a..870f73ec18 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,24 +463,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6345/132723 [00:00<00:01, 63445.83KB/s]
- 11%|# | 13964/132723 [00:00<00:01, 70932.59KB/s]
- 17%|#6 | 22044/132723 [00:00<00:01, 75436.33KB/s]
- 23%|##2 | 30085/132723 [00:00<00:01, 77396.06KB/s]
- 29%|##8 | 38161/132723 [00:00<00:01, 78601.09KB/s]
- 35%|###4 | 46233/132723 [00:00<00:01, 79313.04KB/s]
- 41%|#### | 54323/132723 [00:00<00:00, 79829.69KB/s]
- 47%|####6 | 62306/132723 [00:00<00:00, 79110.79KB/s]
- 53%|#####2 | 70219/132723 [00:00<00:00, 78695.90KB/s]
- 59%|#####8 | 78090/132723 [00:01<00:00, 78193.21KB/s]
- 65%|######4 | 85911/132723 [00:01<00:00, 78030.63KB/s]
- 71%|####### | 93715/132723 [00:01<00:00, 77866.39KB/s]
- 76%|#######6 | 101503/132723 [00:01<00:00, 77839.64KB/s]
- 82%|########2 | 109310/132723 [00:01<00:00, 77906.74KB/s]
- 88%|########8 | 117101/132723 [00:01<00:00, 77696.10KB/s]
- 94%|#########4| 124871/132723 [00:01<00:00, 77658.07KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 77644.07KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 77547.17KB/s]
+ 5%|5 | 7040/132723 [00:00<00:01, 70396.21KB/s]
+ 12%|#1 | 15676/132723 [00:00<00:01, 79783.27KB/s]
+ 18%|#8 | 24367/132723 [00:00<00:01, 83030.90KB/s]
+ 25%|##4 | 32685/132723 [00:00<00:01, 83085.72KB/s]
+ 31%|###1 | 41324/132723 [00:00<00:01, 84271.20KB/s]
+ 38%|###7 | 49956/132723 [00:00<00:00, 84965.27KB/s]
+ 44%|####4 | 58623/132723 [00:00<00:00, 85520.77KB/s]
+ 51%|##### | 67176/132723 [00:00<00:00, 83810.69KB/s]
+ 57%|#####7 | 75881/132723 [00:00<00:00, 84808.04KB/s]
+ 64%|######3 | 84538/132723 [00:01<00:00, 85343.72KB/s]
+ 70%|####### | 93289/132723 [00:01<00:00, 86000.02KB/s]
+ 77%|#######6 | 102026/132723 [00:01<00:00, 86412.90KB/s]
+ 83%|########3 | 110760/132723 [00:01<00:00, 86690.60KB/s]
+ 90%|######### | 119537/132723 [00:01<00:00, 87014.21KB/s]
+ 97%|#########6| 128313/132723 [00:01<00:00, 87235.29KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 85093.56KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -519,7 +517,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 37.969 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 29.198 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 7de778cb98..fdeebcb2bd 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:22.671</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:44.345</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_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>03:37.969</p></td>
+<td><p>03:29.198</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>03:34.346</p></td>
+<td><p>03:20.248</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>02:34.085</p></td>
+<td><p>02:32.389</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>01:47.374</p></td>
+<td><p>01:42.073</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>01:15.782</p></td>
+<td><p>01:12.337</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>00:55.779</p></td>
+<td><p>00:54.771</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>00:41.632</p></td>
+<td><p>00:39.572</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>00:28.077</p></td>
+<td><p>00:27.011</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>00:27.621</p></td>
+<td><p>00:26.740</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 d76c48139a..673e33ca55 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -619,7 +619,7 @@ 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.zip171c635f-144d-48e4-8541-bccc31b7e39e 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.zip0571037d-2a89-43fa-bbdf-71397d663765 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 4aa89d52c2..e3a8db3b6e 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:54.065</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:51.590</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:50.161</p></td>
+<td><p>00:47.907</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>00:02.787</p></td>
+<td><p>00:02.636</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>00:01.109</p></td>
+<td><p>00:01.038</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 0b67afe565..b813014154 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ 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: 21141us [21141us] (48.64%; 48.64%)
-FoldScaleAxis: 22323us [8us] (51.36%; 51.36%)
- FoldConstant: 22315us [1704us] (51.34%; 99.97%)
- InferType: 20611us [20611us] (47.42%; 92.36%)
+InferType: 21025us [21025us] (48.63%; 48.63%)
+FoldScaleAxis: 22205us [7us] (51.37%; 51.37%)
+ FoldConstant: 22199us [1674us] (51.35%; 99.97%)
+ InferType: 20525us [20525us] (47.48%; 92.46%)
</pre></div>
</div>
</div>
@@ -551,10 +551,10 @@ 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: 20666us [20666us] (48.06%; 48.06%)
-FoldScaleAxis: 22331us [7us] (51.94%; 51.94%)
- FoldConstant: 22324us [1720us] (51.92%; 99.97%)
- InferType: 20603us [20603us] (47.92%; 92.29%)
+InferType: 20580us [20580us] (48.44%; 48.44%)
+FoldScaleAxis: 21906us [5us] (51.56%; 51.56%)
+ FoldConstant: 21902us [1663us] (51.55%; 99.98%)
+ InferType: 20239us [20239us] (47.64%; 92.41%)
</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 f29d5f4cfa..4014f4f94f 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -575,7 +575,7 @@ 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: 50.327518 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 45.987808 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 e030f5f2a1..e75b7aa11b 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -867,7 +867,7 @@ 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: 10.019635 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.568201 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 ecec626d04..baf38492ec 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -472,8 +472,8 @@ 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: 0.018697
-Baseline: 3.386919
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017640
+Baseline: 3.298908
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -532,7 +532,7 @@ 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: 0.307382
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301587
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ 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: 0.340299
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.334763
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -644,7 +644,7 @@ 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: 0.118252
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.113063
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -721,7 +721,7 @@ 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: 0.109058
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108578
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ 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: 0.112386
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110367
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -879,7 +879,7 @@ 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: 0.147332
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145990
</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 95c3f94b7f..48c7eafd67 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.118</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.320</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.480</p></td>
+<td><p>00:31.765</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>00:01.547</p></td>
+<td><p>00:01.501</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>00:01.090</p></td>
+<td><p>00:01.054</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 0842c52418..2837aeb68a 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:24.856</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:21.729</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:39.782</p></td>
+<td><p>05:43.646</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>01:40.825</p></td>
+<td><p>01:37.989</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>01:07.028</p></td>
+<td><p>01:05.003</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>00:29.042</p></td>
+<td><p>00:28.091</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>00:14.745</p></td>
+<td><p>00:14.222</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>00:13.435</p></td>
+<td><p>00:12.779</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 ccc7d1c214..0bd5b0fd68 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
@@ -506,487 +506,72 @@ 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.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 32)
+ T.launch_thread(blockIdx_x, 64)
conv2d_nchw = T.allocate([8], "float32", "local")
- pad_temp_shared = T.allocate([2016], "float32", "shared")
- kernel_shared = T.allocate([1536], "float32", "shared")
+ pad_temp_shared = T.allocate([3136], "float32", "shared")
+ kernel_shared = T.allocate([512], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 98)
- conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
+ T.launch_thread(threadIdx_x, 49)
+ conv2d_nchw_1 = T.Buffer((16,), data=conv2d_nchw, scope="local", align=16)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[3] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(16, 3):
- cse_var_4: T.int32 = rc_outer_outer * 1568
- cse_var_3: T.int32 = rc_outer_outer * 288
- cse_var_2: T.int32 = ry_outer_outer * 7
+ for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(8, 3, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 576
cse_var_1: T.int32 = ry_outer_outer * 3
+ pad_temp_shared_1 = T.Buffer((3136,), data=pad_temp_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(64):
+ cse_var_3: T.int32 = ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49
+ threadIdx_x_1 = T.env_thread("threadIdx.x")
+ T.launch_thread(threadIdx_x_1, 49)
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[cse_var_3 + threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 // 7 + ry_outer_outer and threadIdx_x_1 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 3136 + cse_var_3 + ry_outer_outer * 7 + rx_outer_outer + threadIdx_x_1 - 8], T.float32(0))
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((2016,), data=pad_temp_shared, scope="shared")
- data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 * 12] = T.if_then_else(1 <= threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer < 8 and 0 < threadIdx_x_1 % 3, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1] = T.if_then_else(1 <= threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer < 8, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 7], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 2] = T.if_then_else(1 <= threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 4 % 21 // 3 + ry_outer_outer < 8 and threadIdx_x_1 % 3 < 2, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 6], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 3] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 3) % 9 and (threadIdx_x_1 * 3 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 4] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 4) % 9 and (threadIdx_x_1 * 3 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 5] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 5) % 9 and (threadIdx_x_1 * 3 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 5) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 6] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 6) % 9 and (threadIdx_x_1 * 3 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 2) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 7] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 7) % 9 and (threadIdx_x_1 * 3 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 2) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 8] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 2) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 8) % 9 and (threadIdx_x_1 * 3 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 2) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 8) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 9] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 < 8 and 0 < threadIdx_x_1 % 3, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 - 1], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 10] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 < 8, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 12 + 11] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 1) % 7 < 8 and threadIdx_x_1 % 3 < 2, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 1], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 6) % 9 and (threadIdx_x_1 * 3 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 6) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1177] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 7) % 9 and (threadIdx_x_1 * 3 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 7) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1178] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 8) % 9 and (threadIdx_x_1 * 3 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 8) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1179] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 < 8 and 0 < threadIdx_x_1 % 3, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 909], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1180] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 < 8, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 910], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1181] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 4 // 3 + 5) % 7 < 8 and threadIdx_x_1 % 3 < 2, data_1[cse_var_4 + threadIdx_x_1 * 4 // 3 * 7 + cse_var_2 + threadIdx_x_1 % 3 * 3 + 911], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1182] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 3) % 9 and (threadIdx_x_1 * 3 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 394) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 3) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1183] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 3 + 4) % 9 and (threadIdx_x_1 * 3 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 394) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 4) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1184] = T.if_then_else(1 <= (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 4 + 16) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 3 + 5) % 9 and (threadIdx_x_1 * 3 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 394) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 5) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1185] = T.if_then_else(1 <= ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 and ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 < 8 and 1 < (threadIdx_x_1 * 3 + 6) % 9 and (threadIdx_x_1 * 3 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 6) % 9 - 1], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1186] = T.if_then_else(1 <= ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 and ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 < 8 and 1 <= (threadIdx_x_1 * 3 + 7) % 9 and (threadIdx_x_1 * 3 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 7) % 9 - 1], T.float32(0))
- if T.likely(threadIdx_x_1 < 70):
- pad_temp_shared_1[threadIdx_x_1 * 12 + 1187] = T.if_then_else(1 <= ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 and ry_outer_outer + ((threadIdx_x_1 * 4 + 392) // 3 + 1) % 7 < 8 and 1 < (threadIdx_x_1 * 3 + 8) % 9 and (threadIdx_x_1 * 3 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 4 + 392) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 3 + 8) % 9 - 1], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((1536,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((512,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 32 * 4608 + cse_var_3 + threadIdx_x_2 % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 32 * 4608 + cse_var_3 + threadIdx_x_2 % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 32 * 4608 + cse_var_3 + threadIdx_x_2 % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 294] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 2) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 295] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 2) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 296] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 2) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 588] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 4) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 589] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 4) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 590] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 4) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 882] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 6) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 883] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 6) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 884] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 6) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 * 3 + 1176] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 32 * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1177] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 32 * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1178] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 32 * 9 + cse_var_1 + 2]
- with T.launch_thread(threadIdx_x_2, 98):
- if T.likely(threadIdx_x_2 < 22):
- kernel_shared_1[threadIdx_x_2 * 3 + 1470] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 10) * 9 + cse_var_1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1471] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 10) * 9 + cse_var_1 + 1]
- kernel_shared_1[threadIdx_x_2 * 3 + 1472] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 32 * 4608 + cse_var_3 + (threadIdx_x_2 + 10) * 9 + cse_var_1 + 2]
- for rc_outer_inner in range(2):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 384]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 768]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1152]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 96]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 480]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 864]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1248]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 385]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 769]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1153]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 97]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 481]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 865]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1249]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 386]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 770]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1154]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 98]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 482]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 866]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1250]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 387]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 771]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1155]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 99]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 483]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 867]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1251]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 388]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 772]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1156]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 100]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 484]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 868]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1252]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 5]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 389]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 773]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1157]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 101]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 485]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 869]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1253]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 390]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 774]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1158]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 102]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 486]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 870]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1254]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 7]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 391]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 775]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1159]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 103]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 487]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 871]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1255]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 8]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 392]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 776]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1160]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 104]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 488]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 872]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1256]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 393]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 777]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1161]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 105]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 489]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 873]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1257]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 10]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 394]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 778]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1162]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 106]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 490]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 874]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1258]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 11]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 395]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 779]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1163]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 107]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 491]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 875]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1259]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 396]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 780]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1164]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 108]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 492]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 876]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1260]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 13]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 397]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 781]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1165]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 109]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 493]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 877]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1261]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 14]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 398]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 782]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1166]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 110]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 494]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 878]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1262]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 399]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 783]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1167]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 111]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 495]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 879]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1263]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 16]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 400]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 784]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1168]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 112]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 496]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 880]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1264]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 17]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 401]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 785]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1169]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 113]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 497]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 881]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1265]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 402]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 786]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1170]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 114]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 498]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 882]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1266]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 19]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 403]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 787]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1171]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 115]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 499]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 883]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1267]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 20]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 404]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 788]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1172]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 116]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 500]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 884]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1268]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 405]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 789]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1173]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 117]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 501]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 885]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1269]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 22]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 406]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 790]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1174]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 118]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 502]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 886]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1270]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 23]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 407]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 791]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1175]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 119]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 503]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 887]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1271]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 24]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 408]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 792]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1176]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 120]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 504]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 888]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1272]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 25]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 409]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 793]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1177]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 121]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 505]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 889]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1273]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 26]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 410]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 794]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1178]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 122]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 506]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 890]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1274]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 27]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 411]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 795]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1179]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 123]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 507]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 891]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1275]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 28]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 412]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 796]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1180]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 124]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 508]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 892]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1276]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 29]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 413]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 797]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1181]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 125]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 509]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 893]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1277]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 30]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 414]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 798]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1182]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 126]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 510]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 894]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1278]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 31]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 415]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 799]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1183]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 127]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 511]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 895]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1279]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 32]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 416]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 800]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1184]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 128]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 512]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 896]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1280]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 33]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 417]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 801]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1185]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 129]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 513]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 897]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1281]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 34]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 418]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 802]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1186]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 130]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 514]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 898]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1282]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 35]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 419]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 803]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1187]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 131]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 515]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 899]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1283]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 36]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 420]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 804]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1188]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 132]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 516]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 900]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1284]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 37]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 421]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 805]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1189]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 133]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 517]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 901]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1285]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 38]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 422]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 806]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1190]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 134]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 518]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 902]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1286]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 39]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 423]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 807]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1191]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 135]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 519]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 903]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1287]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 40]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 424]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 808]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1192]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 136]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 520]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 904]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1288]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 41]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 425]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 809]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1193]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 137]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 521]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 905]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1289]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 42]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 426]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 810]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1194]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 138]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 522]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 906]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1290]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 43]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 427]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 811]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1195]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 139]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 523]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 907]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1291]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 44]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 428]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 812]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1196]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 140]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 524]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 908]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1292]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 45]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 429]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 813]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1197]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 141]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 525]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 909]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1293]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 46]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 430]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 814]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1198]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 142]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 526]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 910]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1294]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 47]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 431]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 815]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1199]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 143]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 527]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 911]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + rc_outer_inner * 48 + 1295]
- for i1_inner in range(2):
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x * 36864 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 49] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 49) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 49) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 98] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 98) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 34) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 147] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 147) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 19) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 196] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 196) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 4) * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 245] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 245) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 53) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 294] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 294) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 38) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 343] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 343) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 23) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 392] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 392) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ kernel_shared_1[threadIdx_x_1 + 441] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 441) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 57) % 64 * 9 + cse_var_1 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 49):
+ if T.likely(threadIdx_x_1 < 22):
+ kernel_shared_1[threadIdx_x_1 + 490] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_1 + 490) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 42) * 9 + cse_var_1 + rx_outer_outer]
+ for rc_outer_inner, rc_inner in T.grid(8, 8):
+ cse_var_4: T.int32 = rc_outer_inner * 8 + rc_inner
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 256]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 64]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 320]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 128]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 384]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 192]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 392 + rc_inner * 49 + threadIdx_x] * kernel_shared_1[cse_var_4 + 448]
+ for i1_inner in range(4):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49 + 196] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner + 4], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49 + 392] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner + 8], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49 + 588] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner + 12], T.float32(0))
+ compute_1[blockIdx_x * 392 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 8 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + i1_inner * 49 + threadIdx_x + 196] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 8 + i1_inner + 4], T.float32(0))
</pre></div>
</div>
</div>
@@ -1020,7 +605,7 @@ 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: 0.237 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.240 ms
</pre></div>
</div>
</div>
@@ -1049,10 +634,10 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
@@ -1061,19 +646,19 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
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_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=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=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -1096,16 +681,16 @@ 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=3)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=12)
+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=98)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1123,483 +708,57 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[1536];
+ __shared__ float pad_temp_shared[3136];
+ __shared__ float kernel_shared[512];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 12)] = ((((1 <= ((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer) < 8)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((1 <= ((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = ((((1 <= ((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 21) / 3) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.00 [...]
- pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.00 [...]
- pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7)) < 8)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7)) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3))] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 1) % 7)) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 1)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8) [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8 [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1178)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8) [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1179)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7)) < 8)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 909)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1180)] = (((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 910)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1181)] = ((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 3) + 5) % 7)) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) + 911)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1182)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8) [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1183)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8 [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1184)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8) [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1185)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6 [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1186)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + [...]
- }
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1187)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 4) + 392) / 3) + 1) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8 [...]
- }
- kernel_shared[(((int)threadIdx.x) * 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 2) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 295)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 2) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 296)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 2) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 589)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 590)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 6) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 883)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 6) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 884)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 6) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1177)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1178)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
- if (((int)threadIdx.x) < 22) {
- kernel_shared[((((int)threadIdx.x) * 3) + 1470)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 90)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1471)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 91)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1472)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 384)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 768)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1152)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 480)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 864)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1248)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 385)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 769)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1153)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 481)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 865)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1249)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 386)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 770)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1154)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 482)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 866)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1250)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 387)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 771)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1155)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 483)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 867)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1251)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 388)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 772)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1156)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 484)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 868)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1252)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 389)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 773)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1157)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 485)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 869)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1253)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 390)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 774)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1158)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 486)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 870)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1254)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 391)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 775)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1159)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 103)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 487)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 871)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1255)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 392)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 776)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1160)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 104)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 488)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 872)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1256)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 393)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 777)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1161)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 489)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 873)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1257)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 394)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 778)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1162)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 106)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 490)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 874)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1258)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 395)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 779)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1163)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 107)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 491)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 875)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1259)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 396)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 780)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1164)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 492)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 876)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1260)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 397)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 781)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1165)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 109)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 493)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 877)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1261)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 398)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 782)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1166)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 110)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 494)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 878)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1262)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 399)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 783)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1167)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 111)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 495)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 879)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1263)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 400)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 784)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1168)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 112)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 496)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 880)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1264)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 401)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 785)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1169)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 113)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 497)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 881)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1265)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 402)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 786)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1170)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 114)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 498)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 882)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1266)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 403)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 787)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1171)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 115)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 499)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 883)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1267)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 404)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 788)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1172)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 116)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 500)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 884)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1268)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 405)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 789)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1173)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 501)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 885)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1269)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 406)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 790)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1174)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 118)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 502)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 886)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1270)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 407)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 791)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1175)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 119)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 503)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 887)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1271)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 408)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 792)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1176)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 120)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 504)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 888)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1272)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 409)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 793)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1177)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 121)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 505)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 889)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1273)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 410)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 794)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1178)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 122)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 506)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 890)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1274)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 411)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 795)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1179)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 123)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 507)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 891)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1275)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 412)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 796)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1180)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 124)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 508)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 892)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1276)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 413)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 797)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1181)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 125)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 509)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 893)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1277)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 414)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 798)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1182)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 510)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 894)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1278)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 415)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 799)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1183)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 127)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 511)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 895)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1279)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 416)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 800)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1184)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 128)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 512)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 896)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1280)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 417)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 801)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1185)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 129)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 513)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 897)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1281)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 418)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 802)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1186)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 130)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 514)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 898)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1282)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 419)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 803)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1187)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 131)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 515)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 899)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1283)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 420)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 804)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1188)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 132)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 516)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 900)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1284)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 421)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 805)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1189)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 133)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 517)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 901)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1285)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 422)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 806)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1190)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 134)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 518)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 902)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1286)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 423)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 807)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1191)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 519)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 903)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1287)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 40)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 424)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 808)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 136)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 520)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 904)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 41)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 425)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 809)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 137)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 521)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 905)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1289)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 426)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 810)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 138)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 522)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 906)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1290)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 43)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 427)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 811)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 139)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 523)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 907)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 44)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 428)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 812)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1196)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 140)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 524)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 908)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1292)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 429)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 813)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1197)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 141)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 525)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 909)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1293)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 430)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 814)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 142)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 526)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 910)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 431)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 815)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1199)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 143)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 527)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 911)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 48)) + 1295)]));
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 64; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x))] = (((((1 <= ((((int)threadIdx.x) / 7) + ry_outer_outer)) && (((((int)threadIdx.x) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49)) + (ry_outer_outer * 7)) + rx_outer_outer) [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 49) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 34) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 19) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 53) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 38) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 23) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 57) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 22) {
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 378)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 8) + rc_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 256)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 320)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 128)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 384)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 192)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 392) + (rc_inner * 49)) + ((int)threadIdx.x))] * kernel_shared[(((rc_outer_inner * 8) + rc_inner) + 448)]));
+ }
+ }
}
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 196)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 4)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 588)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 12)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 4)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1634,9 +793,10 @@ In the example below we resume the status and do more 5 trials.</p>
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
Get devices for measurement successfully!
+.T
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 39.782 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 43.646 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 38c800d467..ab86c0564c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ 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)
- 7.9185 7.9233 7.9300 7.9022 0.0118
+ 7.8730 7.8724 7.8842 7.8623 0.0090
</pre></div>
</div>
</div>
@@ -938,7 +938,7 @@ 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 7.028 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.003 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 e66e448eb3..3bee4b75a0 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ 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)
- 756.7985 755.3485 759.9386 755.1084 2.2225
+ 750.2198 750.1006 750.6996 749.8592 0.3533
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ 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 40.825 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 37.989 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 37f1de1977..6d5b0bf8cf 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,27 +632,74 @@ 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(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.Buffer((512,), data=compute_1)
- for i_outer_inner in range(2):
- for i_inner_init, j_init in T.grid(16, 16):
- compute_2[i_outer_inner * 256 + i_inner_init * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 32, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 16, 16):
- cse_var_1 = T.var("int32")
+ for i0_outer_i1_outer_fused in T.parallel(16):
+ compute_1 = T.allocate([4096], "float32", "global")
+ compute_2 = T.Buffer((4096,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(2, 2):
+ for i_inner_init in range(64):
+ cse_var_1: T.int32 = i_outer_inner * 2048 + 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(cse_var_2, i0_outer_i1_outer_fused * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 64):
+ cse_var_2 = T.var("int32")
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_2: T.int32 = i0_outer_i1_outer_fused % 32
- if T.likely(elem_idx < placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]):
- 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)
- cse_var_3: T.int32 = i_outer_inner * 256 + i_inner * 16 + j
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 8192 + i_outer_inner * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
- for i0_inner in range(32):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 32 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i0_outer_i1_outer_fused * 2 + nb_j_inner
+ cse_var_19: T.int32 = i_outer_inner * 16384 + i_inner * 256
+ cse_var_18: T.int32 = i_outer_inner * 2048 + 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(128, 32):
+ cse_var_22: T.int32 = i0_inner * 512 + i0_outer_i1_outer_fused * 32 + i1_inner
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 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_4:cse_var_4 + 16], T.Broadcast(T.float32(0), 16))
+ 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>
@@ -686,7 +733,7 @@ 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: 1.658 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.868 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 d035caa62e..645775db74 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.125</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:29.251</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:34.090</p></td>
+<td><p>00:29.219</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 75abec641d..859101b113 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -568,9 +568,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 24.50/24.50 result: MeasureResult(costs=(0.009450592,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.927823066711426, timestamp=1675408284.1870978) [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7562431
-No: 2 GFLOPS: 34.11/34.11 result: MeasureResult(costs=(0.0067868779333333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.17113995552063, timestamp=1675408284.9329607) [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4723222
-No: 3 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -692,8 +690,8 @@ 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, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4850607
-No: 4 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5720156
+No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -815,8 +813,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7076570
-No: 5 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1350091
+No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -938,8 +936,9 @@ 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, 1, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5098814
-No: 6 GFLOPS: 0.00/34.11 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1084210
+No: 4 GFLOPS: 234.98/234.98 result: MeasureResult(costs=(0.0009851961656441718,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.86448335647583, timestamp=1675416424.5687695) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9496804
+No: 5 GFLOPS: 0.00/234.98 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
@@ -1061,162 +1060,500 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9225039
-No: 7 GFLOPS: 0.00/34.11 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)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5791407
+No: 6 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
- 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()
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 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', 0), ('unroll_explicit', 1)],None,5553495
+No: 7 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 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: 0x00007fa80399cfa2
- 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
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1617
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
- 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, 2, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5376717
-No: 8 GFLOPS: 219.53/219.53 result: MeasureResult(costs=(0.0010545141315789473,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5045509338378906, timestamp=1675408294.3802714) [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6014886
-No: 9 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9602668
+No: 8 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8292002
+No: 9 GFLOPS: 0.00/234.98 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:395
+ 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:381
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:276
+ 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:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4126925
+No: 10 GFLOPS: 0.00/234.98 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
@@ -1338,9 +1675,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1053056
-No: 10 GFLOPS: 35.97/219.53 result: MeasureResult(costs=(0.0064353880625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6258225440979004, timestamp=1675408296.2155497) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5930210
-No: 11 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3349256
+No: 11 GFLOPS: 0.00/234.98 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
@@ -1462,8 +1798,8 @@ 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, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6627242
-No: 12 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7804937
+No: 12 GFLOPS: 0.00/234.98 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
@@ -1585,8 +1921,8 @@ 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, 128, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9308877
-No: 13 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9989606
+No: 13 GFLOPS: 0.00/234.98 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
@@ -1708,9 +2044,8 @@ 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4778309
-No: 14 GFLOPS: 69.09/219.53 result: MeasureResult(costs=(0.003350876866666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5380854606628418, timestamp=1675408297.966354) [('tile_f', [-1, 4, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,210046
-No: 15 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3806842
+No: 14 GFLOPS: 0.00/234.98 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
@@ -1832,8 +2167,8 @@ 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, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4905581
-No: 16 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8008466
+No: 15 GFLOPS: 0.00/234.98 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
@@ -1955,8 +2290,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3827802
-No: 17 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2720264
+No: 16 GFLOPS: 0.00/234.98 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
@@ -2078,8 +2413,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1293466
-No: 18 GFLOPS: 0.00/219.53 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5863570
+No: 17 GFLOPS: 0.00/234.98 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
@@ -2201,8 +2536,9 @@ 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, 2, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2317471
-No: 19 GFLOPS: 0.00/219.53 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, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8950972
+No: 18 GFLOPS: 17.71/234.98 result: MeasureResult(costs=(0.013072096,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.992128849029541, timestamp=1675416431.2788076) [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1975313
+No: 19 GFLOPS: 0.00/234.98 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
@@ -2324,8 +2660,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,369957
-No: 20 GFLOPS: 80.00/219.53 result: MeasureResult(costs=(0.002893765457142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5332930088043213, timestamp=1675408299.739333) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3714223
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6611344
+No: 20 GFLOPS: 6.76/234.98 result: MeasureResult(costs=(0.03422482275,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7962653636932373, timestamp=1675416432.1522903) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7645625
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2364,9 +2700,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6014886
+[('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9496804
Finish loading 20 records
-Time cost of this operator: 0.001487
+Time cost of this operator: 0.001338
</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 d6b622f623..ecd724460d 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -643,10 +643,10 @@ 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 314.8 98.72 (1, 2, 10, 10, 3) 2 1 [314.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.12 0.978 (1, 6, 10, 10) 1 1 [3.12]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.301 (1, 1, 10, 10, 3) 1 1 [0.961]
-Total_time - 318.881 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.0 98.706 (1, 2, 10, 10, 3) 2 1 [310.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.108 0.99 (1, 6, 10, 10) 1 1 [3.108]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.304 (1, 1, 10, 10, 3) 1 1 [0.955]
+Total_time - 314.063 - - - - -
</pre></div>
</div>
</div>
@@ -698,10 +698,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 105.7 97.568 (1, 6, 10, 10, 1) 2 1 [105.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.791 1.653 (1, 6, 10, 10) 1 1 [1.791]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.778 (1, 3, 10, 10, 1) 1 1 [0.843]
-Total_time - 108.334 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.2 98.004 (1, 6, 10, 10, 1) 2 1 [134.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.294 (1, 6, 10, 10) 1 1 [1.772]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.701 (1, 1, 10, 10, 3) 1 1 [0.96]
+Total_time - 136.933 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 822229f851..372c3591c3 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -454,7 +454,7 @@ 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, 42.6MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 233MB/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.
@@ -580,7 +580,7 @@ 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 11.778 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.458 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 90ccfedd4d..c3cdce17d5 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -523,7 +523,7 @@ 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/tmpf4ptv5_b/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpn89yh4fo/images/random'
</pre></div>
</div>
</div>
@@ -583,8 +583,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [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/tmpf4ptv5_b/images/target contains 8144 images
-/tmp/tmpf4ptv5_b/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], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [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/tmpn89yh4fo/images/target contains 8144 images
+/tmp/tmpn89yh4fo/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -696,13 +696,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2188 - accuracy: 0.9242 - val_loss: 0.1065 - val_accuracy: 0.9637 - 47s/epoch - 144ms/step
+328/328 - 46s - loss: 0.2156 - accuracy: 0.9249 - val_loss: 0.1436 - val_accuracy: 0.9535 - 46s/epoch - 141ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0937 - accuracy: 0.9659 - val_loss: 0.1405 - val_accuracy: 0.9566 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.1009 - accuracy: 0.9637 - val_loss: 0.1320 - val_accuracy: 0.9539 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0700 - accuracy: 0.9744 - val_loss: 0.0954 - val_accuracy: 0.9721 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0731 - accuracy: 0.9712 - val_loss: 0.0958 - val_accuracy: 0.9679 - 43s/epoch - 130ms/step
-<keras.callbacks.History object at 0x7f863c47fa10>
+<keras.callbacks.History object at 0x7ffabc510f10>
</pre></div>
</div>
</div>
@@ -966,7 +966,7 @@ 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 53.103 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 43.587 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 3eef64e19f..0a0d4e1ff4 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:12.503</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:56.135</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">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>04:53.103</p></td>
+<td><p>04:43.587</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:11.778</p></td>
+<td><p>01:08.458</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:54.117</p></td>
+<td><p>00:51.295</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>00:08.137</p></td>
+<td><p>00:07.702</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>00:05.367</p></td>
+<td><p>00:05.094</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 4e11b022d3..4852c8a092 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.605</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.847</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:33.081</p></td>
+<td><p>00:31.895</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.770</p></td>
+<td><p>00:10.394</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>00:01.748</p></td>
+<td><p>00:01.551</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 963d7c5ded..12b9f6d4d8 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f84e7df2170>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7ff95f560f80>
</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 4635d03859..0e073da664 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:08.831</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.709</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,31 +349,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:06.250</p></td>
+<td><p>00:05.229</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>00:01.200</p></td>
+<td><p>00:01.145</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>00:00.587</p></td>
+<td><p>00:00.568</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>00:00.568</p></td>
+<td><p>00:00.548</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>00:00.113</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>00:00.051</p></td>
+<td><p>00:00.050</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>00:00.033</p></td>
+<td><p>00:00.032</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 0c5dfdc028..6f05e46656 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ class Module:
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmptw2hdwu6/input0.cc'\nsource_filename = \"/tmp/tmptw2hdwu6/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmp2910ew2g/input0.cc'\nsource_filename = \"/tmp/tmp2910ew2g/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
</pre></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index cf5609776e..fb4343f289 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1616,7 +1616,7 @@ 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>
@@ -1900,7 +1900,7 @@ 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 1d89d7a658..c95c2fe2f2 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/d35a8ab13/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 9dc9b762e8..ec01c0db16 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/d35a8ab13/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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 e2a7049587..a3000594bb 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/d35a8ab13/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 5cded6c4ac..d8bee03768 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/d35a8ab13/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 61fce0f2b7..0e365d07ac 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/d35a8ab13/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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 8dd9c8ed02..75e17d52c4 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/d35a8ab13/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index df0e83c982..7abade839e 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 8cd44ae394..cbfd1f1149 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 869f6c6b75..4dbb03448c 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/d35a8ab13/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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 5a8f391502..bb2ca017d1 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 4e9852d358..302d8e793c 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/d35a8ab13/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 414c78ca65..5571e2f4d4 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index f8db29904b..69bff34322 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/d35a8ab13/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index d539c52c49..c6bf89bac0 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/d35a8ab13/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index ba554fd66e..72c01078a8 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/d35a8ab13/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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 edbbf8c53c..432e4019da 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/d35a8ab13/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index f911813b93..647410889b 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/d35a8ab13/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 2adf635d6b..e3559b3919 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/d35a8ab13/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 7646da580f..626237c151 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/d35a8ab13/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 5b7a0624e6..4849771276 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/d35a8ab13/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index b3f542f04b..a6d03bbc4e 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 7455b89935..410104dd2e 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d35a8ab13/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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 614b8b37f0..7f330feff2 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/d35a8ab13/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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 aac134d0e7..09b54953b0 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/d35a8ab13/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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/d35a8ab13/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/209f074e9/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 b3131dace2..14b9f570b4 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 f48166f0b3..bdf3d459ff 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.158</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:29.575</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +349,11 @@
</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>00:31.151</p></td>
+<td><p>00:29.568</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>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 0d5873630c..2df035171b 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -583,7 +583,7 @@ 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 33.40s!
+resnet18_v1 inference graph built in 31.39s!
</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 be248ea075..27e3203106 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -601,7 +601,7 @@ 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 22.59s!
+yolov3-tiny inference graph built in 21.56s!
</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 06dc8bb335..a2e0dca1ba 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:40.185</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:36.504</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -348,12 +348,12 @@
<col style="width: 7%" />
</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>00:50.240</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
+<td><p>00:48.386</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>00:49.945</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
+<td><p>00:48.118</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 f0203a4411..8e247ae571 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.213</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.163</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.741</p></td>
+<td><p>00:02.711</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>00:00.473</p></td>
+<td><p>00:00.452</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 f6ce5fb048..dd6727a8dc 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.788</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.755</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.407</p></td>
+<td><p>00:00.391</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>00:00.381</p></td>
+<td><p>00:00.364</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 d91045fefe..2c4992804e 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -492,6 +492,9 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+</pre></div>
+</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -569,7 +572,7 @@ 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: 95.447 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 98.840 ms
</pre></div>
</div>
</div>
@@ -643,7 +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 18.143 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.477 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 051f50e431..d65238b696 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -680,16 +680,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.09/10.09 result: MeasureResult(costs=(0.026605293799999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7496817111968994, timestamp=1675406725.1395779) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
-No: 2 GFLOPS: 12.27/12.27 result: MeasureResult(costs=(0.0218823138,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5906140804290771, timestamp=1675406726.5292425) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
-No: 3 GFLOPS: 9.25/12.27 result: MeasureResult(costs=(0.0290300618,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7711708545684814, timestamp=1675406727.2573187) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
-No: 4 GFLOPS: 9.24/12.27 result: MeasureResult(costs=(0.0290646116,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6973280906677246, timestamp=1675406728.7544155) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
-No: 5 GFLOPS: 9.88/12.27 result: MeasureResult(costs=(0.0271788372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6953585147857666, timestamp=1675406729.5636196) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 6 GFLOPS: 2.75/12.27 result: MeasureResult(costs=(0.0974577844,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8022475242614746, timestamp=1675406731.3773532) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
-No: 7 GFLOPS: 2.42/12.27 result: MeasureResult(costs=(0.11076174220000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0055735111236572, timestamp=1675406734.1834998) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
-No: 8 GFLOPS: 3.06/12.27 result: MeasureResult(costs=(0.0876125186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.642512321472168, timestamp=1675406735.8364882) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
-No: 9 GFLOPS: 2.25/12.27 result: MeasureResult(costs=(0.11930834939999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1392741203308105, timestamp=1675406738.0958972) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
-No: 10 GFLOPS: 2.37/12.27 result: MeasureResult(costs=(0.113495261,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.055821657180786, timestamp=1675406740.169546) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
+No: 1 GFLOPS: 9.61/9.61 result: MeasureResult(costs=(0.0279437706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7079107761383057, timestamp=1675414896.7156808) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+No: 2 GFLOPS: 1.54/9.61 result: MeasureResult(costs=(0.17420288599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0246503353118896, timestamp=1675414900.4974241) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+No: 3 GFLOPS: 10.64/10.64 result: MeasureResult(costs=(0.025226920999999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6309366226196289, timestamp=1675414901.9013178) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+No: 4 GFLOPS: 10.83/10.83 result: MeasureResult(costs=(0.0247976122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6232948303222656, timestamp=1675414902.5543) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
+No: 5 GFLOPS: 2.88/10.83 result: MeasureResult(costs=(0.0930837148,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7398769855499268, timestamp=1675414904.4685497) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
+No: 6 GFLOPS: 12.82/12.82 result: MeasureResult(costs=(0.0209332462,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5863316059112549, timestamp=1675414905.0601938) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+No: 7 GFLOPS: 14.58/14.58 result: MeasureResult(costs=(0.018415987,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.603083610534668, timestamp=1675414906.3519657) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+No: 8 GFLOPS: 3.69/14.58 result: MeasureResult(costs=(0.0727446234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.403618335723877, timestamp=1675414907.759496) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 9 GFLOPS: 9.13/14.58 result: MeasureResult(costs=(0.029410109400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9025619029998779, timestamp=1675414908.778903) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+No: 10 GFLOPS: 11.48/14.58 result: MeasureResult(costs=(0.023389680000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5853416919708252, timestamp=1675414909.4101672) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
</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 6fe5ea340e..da9ec2b6f9 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -558,7 +558,7 @@ 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': 519.2060856400008, 'median': 518.6517025499995, 'std': 1.923171496934491}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 509.73409502000106, 'median': 509.5896542999981, 'std': 2.5278528585166624}
</pre></div>
</div>
</div>
@@ -710,178 +710,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 21.83/ 21.83 GFLOPS | Progress: (4/20) | 8.09 s
-[Task 1/25] Current/Best: 14.19/ 21.83 GFLOPS | Progress: (8/20) | 12.18 s
-[Task 1/25] Current/Best: 23.32/ 23.32 GFLOPS | Progress: (12/20) | 16.37 s
-[Task 1/25] Current/Best: 11.07/ 23.32 GFLOPS | Progress: (16/20) | 20.12 s
-[Task 1/25] Current/Best: 11.27/ 23.32 GFLOPS | Progress: (20/20) | 23.28 s Done.
+[Task 1/25] Current/Best: 12.63/ 12.63 GFLOPS | Progress: (4/20) | 11.79 s
+[Task 1/25] Current/Best: 9.71/ 17.75 GFLOPS | Progress: (8/20) | 15.03 s
+[Task 1/25] Current/Best: 14.18/ 18.34 GFLOPS | Progress: (12/20) | 17.67 s
+[Task 1/25] Current/Best: 9.97/ 18.34 GFLOPS | Progress: (16/20) | 19.90 s
+[Task 1/25] Current/Best: 22.63/ 23.91 GFLOPS | Progress: (20/20) | 22.99 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 9.24/ 17.96 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 2/25] Current/Best: 10.50/ 20.67 GFLOPS | Progress: (8/20) | 6.45 s
-[Task 2/25] Current/Best: 14.71/ 20.67 GFLOPS | Progress: (12/20) | 7.82 s
-[Task 2/25] Current/Best: 10.17/ 20.67 GFLOPS | Progress: (16/20) | 10.16 s
-[Task 2/25] Current/Best: 17.93/ 20.67 GFLOPS | Progress: (20/20) | 11.91 s Done.
+[Task 2/25] Current/Best: 17.19/ 21.14 GFLOPS | Progress: (4/20) | 3.05 s
+[Task 2/25] Current/Best: 10.06/ 21.14 GFLOPS | Progress: (8/20) | 6.18 s
+[Task 2/25] Current/Best: 7.61/ 21.14 GFLOPS | Progress: (12/20) | 7.52 s
+[Task 2/25] Current/Best: 12.94/ 21.14 GFLOPS | Progress: (16/20) | 9.33 s
+[Task 2/25] Current/Best: 2.03/ 21.14 GFLOPS | Progress: (20/20) | 10.79 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 14.99/ 14.99 GFLOPS | Progress: (4/20) | 4.05 s
-[Task 3/25] Current/Best: 10.61/ 19.50 GFLOPS | Progress: (8/20) | 6.45 s
-[Task 3/25] Current/Best: 11.32/ 19.50 GFLOPS | Progress: (12/20) | 8.76 s
-[Task 3/25] Current/Best: 14.24/ 19.50 GFLOPS | Progress: (16/20) | 11.28 s
-[Task 3/25] Current/Best: 11.03/ 22.49 GFLOPS | Progress: (20/20) | 15.02 s Done.
+[Task 3/25] Current/Best: 13.51/ 14.49 GFLOPS | Progress: (4/20) | 4.25 s
+[Task 3/25] Current/Best: 15.22/ 20.38 GFLOPS | Progress: (8/20) | 6.79 s
+[Task 3/25] Current/Best: 10.70/ 20.38 GFLOPS | Progress: (12/20) | 9.16 s
+[Task 3/25] Current/Best: 5.68/ 20.38 GFLOPS | Progress: (16/20) | 12.03 s
+[Task 3/25] Current/Best: 16.17/ 20.38 GFLOPS | Progress: (20/20) | 14.04 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (4/20) | 4.15 s
-[Task 4/25] Current/Best: 10.85/ 19.99 GFLOPS | Progress: (8/20) | 6.72 s
-[Task 4/25] Current/Best: 15.28/ 19.99 GFLOPS | Progress: (12/20) | 8.48 s
-[Task 4/25] Current/Best: 13.12/ 20.71 GFLOPS | Progress: (16/20) | 13.14 s
-[Task 4/25] Current/Best: 9.64/ 20.71 GFLOPS | Progress: (20/20) | 24.42 s
-[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 5/25] Current/Best: 10.01/ 15.61 GFLOPS | Progress: (4/20) | 4.43 s
-[Task 5/25] Current/Best: 17.70/ 18.54 GFLOPS | Progress: (8/20) | 6.14 s
-[Task 5/25] Current/Best: 10.19/ 21.62 GFLOPS | Progress: (12/20) | 8.19 s
-[Task 5/25] Current/Best: 5.70/ 21.62 GFLOPS | Progress: (16/20) | 11.00 s
-[Task 5/25] Current/Best: 5.58/ 21.62 GFLOPS | Progress: (20/20) | 13.78 s Done.
+[Task 4/25] Current/Best: 13.19/ 18.89 GFLOPS | Progress: (4/20) | 4.01 s
+[Task 4/25] Current/Best: 11.90/ 18.89 GFLOPS | Progress: (8/20) | 6.02 s
+[Task 4/25] Current/Best: 6.52/ 18.89 GFLOPS | Progress: (12/20) | 8.25 s
+[Task 4/25] Current/Best: 13.88/ 18.89 GFLOPS | Progress: (16/20) | 11.17 s
+[Task 4/25] Current/Best: 18.04/ 18.89 GFLOPS | Progress: (20/20) | 13.07 s Done.
+
+[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 5/25] Current/Best: 12.43/ 17.18 GFLOPS | Progress: (4/20) | 3.84 s
+[Task 5/25] Current/Best: 3.07/ 17.18 GFLOPS | Progress: (8/20) | 5.79 s
+[Task 5/25] Current/Best: 14.08/ 17.18 GFLOPS | Progress: (12/20) | 8.38 s
+[Task 5/25] Current/Best: 9.13/ 17.18 GFLOPS | Progress: (16/20) | 11.83 s
+[Task 5/25] Current/Best: 4.75/ 17.18 GFLOPS | Progress: (20/20) | 13.99 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 14.45/ 18.43 GFLOPS | Progress: (4/20) | 4.60 s
-[Task 6/25] Current/Best: 11.72/ 18.43 GFLOPS | Progress: (8/20) | 8.38 s
-[Task 6/25] Current/Best: 17.74/ 18.43 GFLOPS | Progress: (12/20) | 12.18 s
-[Task 6/25] Current/Best: 13.49/ 18.43 GFLOPS | Progress: (16/20) | 15.17 s
-[Task 6/25] Current/Best: 13.99/ 18.43 GFLOPS | Progress: (20/20) | 18.66 s Done.
+[Task 6/25] Current/Best: 16.23/ 16.23 GFLOPS | Progress: (4/20) | 5.34 s
+[Task 6/25] Current/Best: 10.73/ 16.28 GFLOPS | Progress: (8/20) | 7.86 s
+[Task 6/25] Current/Best: 12.96/ 16.28 GFLOPS | Progress: (12/20) | 10.85 s
+[Task 6/25] Current/Best: 6.28/ 16.28 GFLOPS | Progress: (16/20) | 13.99 s
+[Task 6/25] Current/Best: 15.86/ 16.28 GFLOPS | Progress: (20/20) | 16.73 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 15.38/ 20.94 GFLOPS | Progress: (4/20) | 3.94 s
-[Task 7/25] Current/Best: 6.03/ 20.94 GFLOPS | Progress: (8/20) | 6.97 s
-[Task 7/25] Current/Best: 10.33/ 20.94 GFLOPS | Progress: (12/20) | 9.47 s
-[Task 7/25] Current/Best: 11.34/ 20.94 GFLOPS | Progress: (16/20) | 11.97 s
-[Task 7/25] Current/Best: 6.16/ 20.94 GFLOPS | Progress: (20/20) | 14.46 s Done.
+[Task 7/25] Current/Best: 12.63/ 16.49 GFLOPS | Progress: (4/20) | 4.14 s
+[Task 7/25] Current/Best: 13.42/ 19.09 GFLOPS | Progress: (8/20) | 7.07 s
+[Task 7/25] Current/Best: 11.87/ 19.09 GFLOPS | Progress: (12/20) | 10.02 s
+[Task 7/25] Current/Best: 5.54/ 19.09 GFLOPS | Progress: (16/20) | 13.37 s
+[Task 7/25] Current/Best: 10.90/ 19.09 GFLOPS | Progress: (20/20) | 15.65 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 3.60/ 13.72 GFLOPS | Progress: (4/20) | 13.73 s
-[Task 8/25] Current/Best: 12.34/ 13.72 GFLOPS | Progress: (8/20) | 19.50 s
-[Task 8/25] Current/Best: 6.54/ 18.55 GFLOPS | Progress: (12/20) | 23.08 s
-[Task 8/25] Current/Best: 7.56/ 18.55 GFLOPS | Progress: (16/20) | 27.63 s
-[Task 8/25] Current/Best: 12.71/ 18.55 GFLOPS | Progress: (20/20) | 30.19 s
-[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 16.01/ 17.20 GFLOPS | Progress: (4/20) | 3.63 s
-[Task 9/25] Current/Best: 13.13/ 21.97 GFLOPS | Progress: (8/20) | 9.87 s
-[Task 9/25] Current/Best: 10.43/ 21.97 GFLOPS | Progress: (12/20) | 12.35 s
-[Task 9/25] Current/Best: 15.89/ 22.27 GFLOPS | Progress: (16/20) | 17.55 s
-[Task 9/25] Current/Best: 14.44/ 22.27 GFLOPS | Progress: (20/20) | 20.32 s Done.
+[Task 8/25] Current/Best: 8.26/ 13.92 GFLOPS | Progress: (4/20) | 6.61 s
+[Task 8/25] Current/Best: 11.88/ 17.97 GFLOPS | Progress: (8/20) | 12.69 s
+[Task 8/25] Current/Best: 14.97/ 17.97 GFLOPS | Progress: (12/20) | 14.79 s
+[Task 8/25] Current/Best: 13.56/ 20.11 GFLOPS | Progress: (16/20) | 18.20 s
+[Task 8/25] Current/Best: 9.44/ 20.11 GFLOPS | Progress: (20/20) | 21.82 s Done.
+[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 9/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (4/20) | 3.46 s
+[Task 9/25] Current/Best: 9.05/ 22.19 GFLOPS | Progress: (8/20) | 11.84 s
+[Task 9/25] Current/Best: 12.28/ 22.19 GFLOPS | Progress: (12/20) | 23.00 s
+[Task 9/25] Current/Best: 14.96/ 22.19 GFLOPS | Progress: (16/20) | 28.60 s
+[Task 9/25] Current/Best: 6.13/ 22.19 GFLOPS | Progress: (20/20) | 37.59 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 5.98/ 10.79 GFLOPS | Progress: (4/20) | 4.82 s
-[Task 10/25] Current/Best: 11.28/ 19.12 GFLOPS | Progress: (8/20) | 6.97 s
-[Task 10/25] Current/Best: 15.78/ 19.12 GFLOPS | Progress: (12/20) | 9.07 s
-[Task 10/25] Current/Best: 3.04/ 19.12 GFLOPS | Progress: (16/20) | 13.15 s
-[Task 10/25] Current/Best: 13.49/ 19.12 GFLOPS | Progress: (20/20) | 16.17 s Done.
+[Task 10/25] Current/Best: 9.75/ 13.00 GFLOPS | Progress: (4/20) | 4.30 s
+[Task 10/25] Current/Best: 3.14/ 16.12 GFLOPS | Progress: (8/20) | 6.24 s
+[Task 10/25] Current/Best: 6.51/ 16.12 GFLOPS | Progress: (12/20) | 8.20 s
+[Task 10/25] Current/Best: 9.27/ 16.12 GFLOPS | Progress: (16/20) | 10.17 s
+[Task 10/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (20/20) | 12.76 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 3.11/ 17.30 GFLOPS | Progress: (4/20) | 4.99 s
-[Task 11/25] Current/Best: 8.86/ 17.30 GFLOPS | Progress: (8/20) | 7.89 s
-[Task 11/25] Current/Best: 7.72/ 17.30 GFLOPS | Progress: (12/20) | 10.42 s
-[Task 11/25] Current/Best: 6.18/ 17.30 GFLOPS | Progress: (16/20) | 13.74 s
-[Task 11/25] Current/Best: 14.32/ 17.30 GFLOPS | Progress: (20/20) | 16.50 s Done.
+[Task 11/25] Current/Best: 19.39/ 19.39 GFLOPS | Progress: (4/20) | 4.49 s
+[Task 11/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 11/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (12/20) | 8.93 s
+[Task 11/25] Current/Best: 17.86/ 21.35 GFLOPS | Progress: (16/20) | 11.68 s
+[Task 11/25] Current/Best: 18.45/ 21.35 GFLOPS | Progress: (20/20) | 14.38 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 13.29/ 19.30 GFLOPS | Progress: (4/20) | 4.89 s
-[Task 12/25] Current/Best: 15.00/ 19.30 GFLOPS | Progress: (8/20) | 7.61 s
-[Task 12/25] Current/Best: 10.54/ 19.30 GFLOPS | Progress: (12/20) | 9.94 s
-[Task 12/25] Current/Best: 13.17/ 19.30 GFLOPS | Progress: (16/20) | 16.54 s
-[Task 12/25] Current/Best: 9.13/ 19.30 GFLOPS | Progress: (20/20) | 18.78 s Done.
+[Task 12/25] Current/Best: 8.30/ 15.54 GFLOPS | Progress: (4/20) | 4.35 s
+[Task 12/25] Current/Best: 5.39/ 15.54 GFLOPS | Progress: (8/20) | 6.98 s
+[Task 12/25] Current/Best: 3.54/ 15.54 GFLOPS | Progress: (12/20) | 11.09 s
+[Task 12/25] Current/Best: 6.49/ 15.72 GFLOPS | Progress: (16/20) | 13.79 s
+[Task 12/25] Current/Best: 18.93/ 20.65 GFLOPS | Progress: (20/20) | 15.79 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 13.09/ 17.32 GFLOPS | Progress: (4/20) | 4.51 s
-[Task 13/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (8/20) | 6.65 s
-[Task 13/25] Current/Best: 13.18/ 22.37 GFLOPS | Progress: (12/20) | 9.98 s
-[Task 13/25] Current/Best: 18.27/ 22.37 GFLOPS | Progress: (16/20) | 13.17 s
-[Task 13/25] Current/Best: 17.71/ 22.37 GFLOPS | Progress: (20/20) | 17.14 s Done.
+[Task 13/25] Current/Best: 9.21/ 13.88 GFLOPS | Progress: (4/20) | 5.10 s
+[Task 13/25] Current/Best: 9.14/ 22.97 GFLOPS | Progress: (8/20) | 7.77 s
+[Task 13/25] Current/Best: 11.50/ 22.97 GFLOPS | Progress: (12/20) | 11.83 s
+[Task 13/25] Current/Best: 11.39/ 22.97 GFLOPS | Progress: (16/20) | 15.69 s
+[Task 13/25] Current/Best: 15.05/ 22.97 GFLOPS | Progress: (20/20) | 18.03 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 14/25] Current/Best: 12.19/ 19.58 GFLOPS | Progress: (8/20) | 5.43 s
-[Task 14/25] Current/Best: 8.92/ 19.58 GFLOPS | Progress: (12/20) | 11.47 s Done.
-
-[Task 14/25] Current/Best: 14.94/ 19.58 GFLOPS | Progress: (16/20) | 13.58 s
-[Task 14/25] Current/Best: 14.17/ 19.58 GFLOPS | Progress: (20/20) | 16.59 s
+[Task 14/25] Current/Best: 11.05/ 21.91 GFLOPS | Progress: (4/20) | 5.09 s
+[Task 14/25] Current/Best: 9.87/ 21.91 GFLOPS | Progress: (8/20) | 10.46 s
+[Task 14/25] Current/Best: 12.71/ 21.91 GFLOPS | Progress: (12/20) | 13.38 s
+[Task 14/25] Current/Best: 12.01/ 21.91 GFLOPS | Progress: (16/20) | 17.36 s
+[Task 14/25] Current/Best: 18.37/ 21.91 GFLOPS | Progress: (20/20) | 20.60 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 13.15/ 19.02 GFLOPS | Progress: (4/20) | 4.87 s
-[Task 15/25] Current/Best: 11.52/ 20.25 GFLOPS | Progress: (8/20) | 8.71 s
-[Task 15/25] Current/Best: 11.35/ 20.25 GFLOPS | Progress: (12/20) | 13.44 s
-[Task 15/25] Current/Best: 12.79/ 20.33 GFLOPS | Progress: (16/20) | 15.03 s
-[Task 15/25] Current/Best: 15.04/ 20.33 GFLOPS | Progress: (20/20) | 16.81 s
+[Task 15/25] Current/Best: 13.47/ 13.47 GFLOPS | Progress: (4/20) | 3.60 s Done.
+ Done.
+
+[Task 15/25] Current/Best: 18.42/ 23.18 GFLOPS | Progress: (8/20) | 5.83 s
+[Task 15/25] Current/Best: 8.69/ 23.18 GFLOPS | Progress: (12/20) | 10.67 s
+[Task 15/25] Current/Best: 14.59/ 23.18 GFLOPS | Progress: (16/20) | 14.04 s
+[Task 15/25] Current/Best: 8.47/ 23.18 GFLOPS | Progress: (20/20) | 16.62 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 11.64/ 12.90 GFLOPS | Progress: (4/20) | 4.85 s
-[Task 16/25] Current/Best: 6.17/ 17.72 GFLOPS | Progress: (8/20) | 7.27 s
-[Task 16/25] Current/Best: 19.74/ 19.74 GFLOPS | Progress: (12/20) | 9.18 s
-[Task 16/25] Current/Best: 10.38/ 19.74 GFLOPS | Progress: (16/20) | 11.94 s
-[Task 16/25] Current/Best: 18.09/ 20.47 GFLOPS | Progress: (20/20) | 13.64 s Done.
+[Task 16/25] Current/Best: 14.01/ 18.58 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 16/25] Current/Best: 9.17/ 18.58 GFLOPS | Progress: (8/20) | 5.56 s
+[Task 16/25] Current/Best: 14.91/ 18.58 GFLOPS | Progress: (12/20) | 9.35 s
+[Task 16/25] Current/Best: 18.96/ 21.44 GFLOPS | Progress: (16/20) | 10.78 s
+[Task 16/25] Current/Best: 14.62/ 21.44 GFLOPS | Progress: (20/20) | 12.64 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 6.43/ 10.21 GFLOPS | Progress: (4/20) | 4.87 s
-[Task 17/25] Current/Best: 9.83/ 18.36 GFLOPS | Progress: (8/20) | 6.96 s
-[Task 17/25] Current/Best: 23.11/ 23.11 GFLOPS | Progress: (12/20) | 9.37 s
-[Task 17/25] Current/Best: 13.48/ 23.11 GFLOPS | Progress: (16/20) | 11.94 s
-[Task 17/25] Current/Best: 11.17/ 23.11 GFLOPS | Progress: (20/20) | 15.08 s Done.
+[Task 17/25] Current/Best: 10.56/ 18.60 GFLOPS | Progress: (4/20) | 4.75 s
+[Task 17/25] Current/Best: 16.93/ 21.69 GFLOPS | Progress: (8/20) | 7.21 s
+[Task 17/25] Current/Best: 7.66/ 21.69 GFLOPS | Progress: (12/20) | 11.43 s
+[Task 17/25] Current/Best: 16.07/ 21.69 GFLOPS | Progress: (16/20) | 14.78 s
+[Task 17/25] Current/Best: 17.13/ 21.69 GFLOPS | Progress: (20/20) | 17.23 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 15.64/ 15.64 GFLOPS | Progress: (4/20) | 4.08 s
-[Task 18/25] Current/Best: 11.89/ 17.35 GFLOPS | Progress: (8/20) | 8.37 s
-[Task 18/25] Current/Best: 20.78/ 20.78 GFLOPS | Progress: (12/20) | 11.85 s
-[Task 18/25] Current/Best: 19.03/ 20.78 GFLOPS | Progress: (16/20) | 14.04 s
-[Task 18/25] Current/Best: 11.10/ 20.78 GFLOPS | Progress: (20/20) | 17.28 s Done.
+[Task 18/25] Current/Best: 12.24/ 20.38 GFLOPS | Progress: (4/20) | 3.88 s
+[Task 18/25] Current/Best: 14.27/ 20.38 GFLOPS | Progress: (8/20) | 5.99 s
+[Task 18/25] Current/Best: 15.07/ 20.38 GFLOPS | Progress: (12/20) | 8.11 s
+[Task 18/25] Current/Best: 14.21/ 20.38 GFLOPS | Progress: (16/20) | 10.55 s
+[Task 18/25] Current/Best: 10.25/ 20.38 GFLOPS | Progress: (20/20) | 12.76 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 2.69/ 21.25 GFLOPS | Progress: (4/20) | 6.03 s
-[Task 19/25] Current/Best: 18.04/ 21.25 GFLOPS | Progress: (8/20) | 11.58 s
-[Task 19/25] Current/Best: 19.84/ 21.25 GFLOPS | Progress: (12/20) | 15.77 s
-[Task 19/25] Current/Best: 10.72/ 21.25 GFLOPS | Progress: (16/20) | 18.58 s
-[Task 19/25] Current/Best: 17.82/ 21.25 GFLOPS | Progress: (20/20) | 20.84 s Done.
+[Task 19/25] Current/Best: 5.36/ 11.43 GFLOPS | Progress: (4/20) | 4.76 s
+[Task 19/25] Current/Best: 6.18/ 19.37 GFLOPS | Progress: (8/20) | 7.30 s
+[Task 19/25] Current/Best: 3.09/ 22.65 GFLOPS | Progress: (12/20) | 11.21 s
+[Task 19/25] Current/Best: 9.21/ 22.65 GFLOPS | Progress: (16/20) | 13.89 s
+[Task 19/25] Current/Best: 6.19/ 22.65 GFLOPS | Progress: (20/20) | 17.67 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.30/ 11.99 GFLOPS | Progress: (4/20) | 5.97 s
-[Task 20/25] Current/Best: 11.44/ 13.73 GFLOPS | Progress: (8/20) | 9.61 s
-[Task 20/25] Current/Best: 16.61/ 16.61 GFLOPS | Progress: (12/20) | 12.94 s
-[Task 20/25] Current/Best: 17.24/ 17.24 GFLOPS | Progress: (16/20) | 15.95 s
-[Task 20/25] Current/Best: 4.14/ 17.24 GFLOPS | Progress: (20/20) | 19.36 s
+[Task 20/25] Current/Best: 12.89/ 16.18 GFLOPS | Progress: (4/20) | 4.78 s
+[Task 20/25] Current/Best: 10.44/ 18.50 GFLOPS | Progress: (8/20) | 8.70 s
+[Task 20/25] Current/Best: 17.73/ 18.50 GFLOPS | Progress: (12/20) | 11.36 s
+[Task 20/25] Current/Best: 8.05/ 18.50 GFLOPS | Progress: (16/20) | 13.81 s
+[Task 20/25] Current/Best: 7.56/ 19.47 GFLOPS | Progress: (20/20) | 15.90 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 12.74/ 18.26 GFLOPS | Progress: (4/20) | 3.37 s Done.
- Done.
+[Task 21/25] Current/Best: 8.84/ 17.03 GFLOPS | Progress: (4/20) | 5.83 s
+[Task 21/25] Current/Best: 1.62/ 17.03 GFLOPS | Progress: (8/20) | 7.93 s
+[Task 21/25] Current/Best: 3.10/ 17.03 GFLOPS | Progress: (12/20) | 10.16 s
+[Task 21/25] Current/Best: 12.97/ 17.03 GFLOPS | Progress: (16/20) | 13.26 s Done.
Done.
-[Task 21/25] Current/Best: 14.41/ 18.26 GFLOPS | Progress: (8/20) | 5.76 s
-[Task 21/25] Current/Best: 8.72/ 21.18 GFLOPS | Progress: (12/20) | 8.16 s
-[Task 21/25] Current/Best: 12.01/ 21.18 GFLOPS | Progress: (16/20) | 9.87 s
-[Task 21/25] Current/Best: 10.87/ 21.18 GFLOPS | Progress: (20/20) | 11.85 s
+[Task 21/25] Current/Best: 17.97/ 17.97 GFLOPS | Progress: (20/20) | 15.06 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 11.67/ 15.74 GFLOPS | Progress: (4/20) | 4.49 s
-[Task 22/25] Current/Best: 17.24/ 18.12 GFLOPS | Progress: (8/20) | 6.47 s
-[Task 22/25] Current/Best: 5.48/ 18.12 GFLOPS | Progress: (12/20) | 8.88 s
-[Task 22/25] Current/Best: 23.04/ 23.04 GFLOPS | Progress: (16/20) | 10.45 s
-[Task 22/25] Current/Best: 16.23/ 23.04 GFLOPS | Progress: (20/20) | 12.29 s Done.
+[Task 22/25] Current/Best: 23.04/ 23.04 GFLOPS | Progress: (4/20) | 4.16 s
+[Task 22/25] Current/Best: 5.21/ 23.04 GFLOPS | Progress: (8/20) | 6.54 s
+[Task 22/25] Current/Best: 11.35/ 23.04 GFLOPS | Progress: (12/20) | 8.39 s
+[Task 22/25] Current/Best: 4.81/ 23.04 GFLOPS | Progress: (16/20) | 10.69 s
+[Task 22/25] Current/Best: 19.83/ 23.04 GFLOPS | Progress: (20/20) | 12.41 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 11.26/ 19.49 GFLOPS | Progress: (4/20) | 7.53 s
-[Task 23/25] Current/Best: 1.55/ 19.49 GFLOPS | Progress: (8/20) | 12.92 s
-[Task 23/25] Current/Best: 10.68/ 19.49 GFLOPS | Progress: (12/20) | 15.77 s
-[Task 23/25] Current/Best: 11.95/ 19.49 GFLOPS | Progress: (16/20) | 17.96 s
-[Task 23/25] Current/Best: 5.02/ 19.49 GFLOPS | Progress: (20/20) | 23.51 s Done.
+[Task 23/25] Current/Best: 12.47/ 23.18 GFLOPS | Progress: (4/20) | 6.92 s
+[Task 23/25] Current/Best: 8.20/ 23.18 GFLOPS | Progress: (8/20) | 10.47 s
+[Task 23/25] Current/Best: 10.95/ 23.18 GFLOPS | Progress: (12/20) | 13.40 s
+[Task 23/25] Current/Best: 23.30/ 23.30 GFLOPS | Progress: (16/20) | 15.86 s
+[Task 23/25] Current/Best: 12.36/ 23.30 GFLOPS | Progress: (20/20) | 18.91 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 6.36/ 6.36 GFLOPS | Progress: (4/20) | 4.60 s
-[Task 24/25] Current/Best: 1.97/ 6.36 GFLOPS | Progress: (8/20) | 15.57 s
-[Task 24/25] Current/Best: 7.79/ 7.79 GFLOPS | Progress: (12/20) | 27.21 s
-[Task 24/25] Current/Best: 0.94/ 8.81 GFLOPS | Progress: (16/20) | 38.18 s
-[Task 24/25] Current/Best: 3.53/ 9.30 GFLOPS | Progress: (20/20) | 49.13 s
+[Task 24/25] Current/Best: 0.58/ 9.86 GFLOPS | Progress: (4/20) | 3.99 s
+[Task 24/25] Current/Best: 3.67/ 9.86 GFLOPS | Progress: (8/20) | 14.65 s
+[Task 24/25] Current/Best: 2.33/ 10.74 GFLOPS | Progress: (12/20) | 26.43 s
+[Task 24/25] Current/Best: 1.55/ 10.74 GFLOPS | Progress: (16/20) | 37.91 s
+[Task 24/25] Current/Best: 2.33/ 10.74 GFLOPS | Progress: (20/20) | 50.00 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-[Task 25/25] Current/Best: 2.98/ 7.61 GFLOPS | Progress: (4/20) | 5.67 s
-[Task 25/25] Current/Best: 1.51/ 7.61 GFLOPS | Progress: (8/20) | 16.66 s
-[Task 25/25] Current/Best: 3.62/ 9.09 GFLOPS | Progress: (12/20) | 28.72 s
-[Task 25/25] Current/Best: 8.64/ 9.09 GFLOPS | Progress: (16/20) | 39.65 s
-[Task 25/25] Current/Best: 7.23/ 9.28 GFLOPS | Progress: (20/20) | 50.58 s
+[Task 25/25] Current/Best: 3.02/ 8.71 GFLOPS | Progress: (4/20) | 12.44 s
+[Task 25/25] Current/Best: 8.69/ 8.71 GFLOPS | Progress: (8/20) | 24.22 s
+[Task 25/25] Current/Best: 1.55/ 8.71 GFLOPS | Progress: (12/20) | 35.16 s
+[Task 25/25] Current/Best: 8.07/ 9.31 GFLOPS | Progress: (16/20) | 46.08 s
+[Task 25/25] Current/Best: 4.47/ 9.31 GFLOPS | Progress: (20/20) | 57.58 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -980,8 +980,8 @@ 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': 422.1551961599971, 'median': 422.1609129499939, 'std': 1.4842894634763848}
-unoptimized: {'mean': 519.2060856400008, 'median': 518.6517025499995, 'std': 1.923171496934491}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 417.8435154399949, 'median': 417.04131054999607, 'std': 2.5236392821839067}
+unoptimized: {'mean': 509.73409502000106, 'median': 509.5896542999981, 'std': 2.5278528585166624}
</pre></div>
</div>
</div>
@@ -995,7 +995,7 @@ 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 16.205 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 57.068 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 f9a9dd8caa..b2cfa12ba8 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -538,7 +538,7 @@ 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>1.238e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.35e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index f86249b402..8b593b1291 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -515,7 +515,7 @@ 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, 0x12970fe0)), stage(b, placeholder(b, 0x22bbd970)), 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, 0x226ad3d0)), stage(b, placeholder(b, 0x9b9dc40)), 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 fda0fe0571..0caed03ef8 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:34.008</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:32.925</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>12:16.205</p></td>
+<td><p>11:57.068</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:18.143</p></td>
+<td><p>01:41.477</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.057</p></td>
+<td><p>00:59.348</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>00:36.091</p></td>
+<td><p>00:35.005</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>00:20.017</p></td>
+<td><p>00:17.580</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="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>00:01.484</p></td>
+<td><p>00:01.467</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>00:00.838</p></td>
+<td><p>00:00.822</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>00:00.174</p></td>
+<td><p>00:00.158</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 a900ec6da8..f385063381 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -687,10 +687,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.13895999979286e-06 1.0
- naive 6.668599999999999e-06 0.9341136524358578
-parallel 7.3086e-06 1.0237625648850899
- vector 2.46032e-05 3.446328316829604
+ numpy 7.248970000546251e-06 1.0
+ naive 6.642e-06 0.9162681042271507
+parallel 7.063099999999999e-06 0.9743591157733795
+ vector 2.4587000000000004e-05 3.3917922129829803
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1006,7 +1006,7 @@ 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: 0.018986
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017485
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1047,7 +1047,7 @@ 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: 3.392148
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.306402
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1111,7 +1111,7 @@ 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: 0.309954
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.293836
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1160,7 +1160,7 @@ 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: 0.346129
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.333988
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1209,7 +1209,7 @@ 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: 0.116968
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.113655
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1279,7 +1279,7 @@ 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: 0.107733
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109073
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1345,7 +1345,7 @@ 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: 0.110402
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110776
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1402,7 +1402,7 @@ 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: 0.146132
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146266
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1455,13 +1455,13 @@ 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 3.3921479667 1.0
- blocking 0.3099542307 0.09137403018463676
- vectorization 0.34612859 0.10203817563321861
-loop permutation 0.11696775210000002 0.034481913303384085
- array packing 0.1077331579 0.03175956914544815
- block caching 0.1104019172 0.03254631527981453
- parallelization 0.1461321517 0.04307953342087328
+ none 3.3064016510000003 1.0
+ blocking 0.2938362989 0.08886890641708066
+ vectorization 0.3339881545 0.10101257794829234
+loop permutation 0.1136548737 0.034374188527768794
+ array packing 0.1090731691 0.03298848131986975
+ block caching 0.11077565 0.033503385762735934
+ parallelization 0.14626609029999998 0.04423724209542502
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1493,7 +1493,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.057 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>