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 2023/02/23 01:26:49 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@a3b51f11b26d721980858091c2df4c7487388c12)
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 2bd0986c6b deploying docs (apache/tvm@a3b51f11b26d721980858091c2df4c7487388c12)
2bd0986c6b is described below
commit 2bd0986c6b3899429ec0d10946a4887e83d46f4c
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Feb 23 01:26:43 2023 +0000
deploying docs (apache/tvm@a3b51f11b26d721980858091c2df4c7487388c12)
---
.../micro_aot.ipynb | 2 +-
.../f8a7209a0e66b246185bfc41bbc82f54/micro_aot.py | 4 +-
docs/_images/sphx_glr_micro_train_001.png | Bin 350060 -> 344888 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24706 -> 24077 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 | 44 +-
.../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 | 1749 ++++++++++----------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 99 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 201 +--
.../how_to/work_with_microtvm/micro_aot.rst.txt | 4 +-
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 60 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 51 +-
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 | 16 +-
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 | 28 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 52 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../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 | 1749 ++++++++++----------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 99 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 201 +--
docs/how_to/work_with_microtvm/micro_aot.html | 4 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 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/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
docs/reference/api/typedoc/classes/instance.html | 58 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 124 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 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 | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 278 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 47 +-
134 files changed, 2749 insertions(+), 3102 deletions(-)
diff --git a/docs/_downloads/c00933f3fbcf90c4f584d54607b33805/micro_aot.ipynb b/docs/_downloads/c00933f3fbcf90c4f584d54607b33805/micro_aot.ipynb
index ade5028b6b..7ffdcb81be 100644
--- a/docs/_downloads/c00933f3fbcf90c4f584d54607b33805/micro_aot.ipynb
+++ b/docs/_downloads/c00933f3fbcf90c4f584d54607b33805/micro_aot.ipynb
@@ -98,7 +98,7 @@
},
"outputs": [],
"source": [
- "MODEL_URL = \"https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/model/keyword_spotting_quant.tflite\"\nMODEL_PATH = download_testdata(MODEL_URL, \"keyword_spotting_quant.tflite\", module=\"model\")\nSAMPLE_URL = \"https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/data/keyword_spotting_int8_6.pyc.npy\"\nSAMPLE_PATH = download_testdata(SAMPLE_URL, \"keyword_spotting_int8_6.pyc.npy\", module=\"data\")\n\ntflite_model_buf = open(MODEL_PATH, \"rb\").read() [...]
+ "MODEL_URL = \"https://github.com/mlcommons/tiny/raw/bceb91c5ad2e2deb295547d81505721d3a87d578/benchmark/training/keyword_spotting/trained_models/kws_ref_model.tflite\"\nMODEL_PATH = download_testdata(MODEL_URL, \"kws_ref_model.tflite\", module=\"model\")\nSAMPLE_URL = \"https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/data/keyword_spotting_int8_6.pyc.npy\"\nSAMPLE_PATH = download_testdata(SAMPLE_URL, \"keyword_spotting_int8_6.pyc.npy\", module=\"data\")\n\ntflite_m [...]
]
},
{
diff --git a/docs/_downloads/f8a7209a0e66b246185bfc41bbc82f54/micro_aot.py b/docs/_downloads/f8a7209a0e66b246185bfc41bbc82f54/micro_aot.py
index f31ffa1570..f07731c183 100644
--- a/docs/_downloads/f8a7209a0e66b246185bfc41bbc82f54/micro_aot.py
+++ b/docs/_downloads/f8a7209a0e66b246185bfc41bbc82f54/micro_aot.py
@@ -74,8 +74,8 @@ from tvm.contrib.download import download_testdata
# **Note:** By default this tutorial runs on x86 CPU using CRT, if you would like to run on Zephyr platform
# you need to export `TVM_MICRO_USE_HW` environment variable.
#
-MODEL_URL = "https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/model/keyword_spotting_quant.tflite"
-MODEL_PATH = download_testdata(MODEL_URL, "keyword_spotting_quant.tflite", module="model")
+MODEL_URL = "https://github.com/mlcommons/tiny/raw/bceb91c5ad2e2deb295547d81505721d3a87d578/benchmark/training/keyword_spotting/trained_models/kws_ref_model.tflite"
+MODEL_PATH = download_testdata(MODEL_URL, "kws_ref_model.tflite", module="model")
SAMPLE_URL = "https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/data/keyword_spotting_int8_6.pyc.npy"
SAMPLE_PATH = download_testdata(SAMPLE_URL, "keyword_spotting_int8_6.pyc.npy", module="data")
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 1f1ec0db70..03eff51625 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 dba2765cb6..ce827177eb 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 309a1887cf..8197688926 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 17.563 seconds)
+ **Total running time of the script:** ( 1 minutes 18.793 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 5a84dca18c..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 917ms/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 29054c8523..12527f0c27 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.zipf9cef832-0fee-4433-88d4-5f1cee5f9164 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip14c31332-78a6-4c8f-b504-c8bb0ecb9b7c 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 4c5b4320c2..c44061f08d 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]
19%|#9 | 7.99M/41.5M [00:00<00:00, 44.3MB/s]
38%|###7 | 15.7M/41.5M [00:00<00:00, 60.0MB/s]
53%|#####2 | 22.0M/41.5M [00:00<00:00, 58.3MB/s]
67%|######7 | 27.8M/41.5M [00:00<00:00, 36.5MB/s]
84%|########3 | 34.7M/41.5M [00:00<00:00, 42.0MB/s]
95%|#########4| 39.4M/41.5M [00:00<00:00, 43.2MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 43.2MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 41.8MB/s]
25%|##4 | 10.3M/41.5M [00:00<00:00, 35.6MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 31.5MB/s]
42%|####1 | 17.3M/41.5M [00:00<00:00, 26.5MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.2MB/s]
61%|######1 | 25.4M/41.5M [00:00<00:00, 26.7MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 31.2MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 36.0MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 30.7MB/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 18ef68c678..e8db668b19 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]
14%|#4 | 6.30M/44.7M [00:00<00:01, 36.8MB/s]
32%|###2 | 14.3M/44.7M [00:00<00:00, 42.6MB/s]
41%|####1 | 18.4M/44.7M [00:00<00:00, 38.7MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 41.3MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 46.1MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 48.8MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 49.0MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
11%|#1 | 5.10M/44.7M [00:00<00:00, 53.5MB/s]
32%|###2 | 14.3M/44.7M [00:00<00:00, 49.1MB/s]
60%|#####9 | 26.7M/44.7M [00:00<00:00, 76.8MB/s]
78%|#######8 | 34.9M/44.7M [00:00<00:00, 70.9MB/s]
97%|#########7| 43.4M/44.7M [00:00<00:00, 76.3MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 72.5MB/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 53bf18161b..ad1f0db36d 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 21.727 seconds)
+ **Total running time of the script:** ( 1 minutes 23.761 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 d9a02eb12d..e2cd680463 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
=================
-**06:21.320** total execution time for **how_to_compile_models** files:
+**06:32.485** total execution time for **how_to_compile_models** files:
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:21.727 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:17.563 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:51.258 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:35.393 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.493 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:30.422 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.294 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.376 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:20.235 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.559 | 0.0 MB |
-+-----------------------------------------------------------------------------------+-----------+--------+
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:23.761 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:18.793 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:53.328 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.162 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:31.318 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.940 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.217 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:25.336 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:20.1000 | 0.0 MB |
++-----------------------------------------------------------------------------------+------------+--------+
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.632 | 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 3d12283707..212faf8711 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)
- 2648.5399 2647.9239 2652.3422 2646.6950 1.7195
+ 2685.3294 2685.0219 2688.8547 2682.1079 2.1227
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 cdc6d6b66d..753b7abb7b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7196 15.5925 16.4317 15.2395 0.4071
+ 16.2886 16.4937 16.5457 15.5124 0.3864
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 69d0291e24..b3a0a794a3 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 | 7.99M/170M [00:00<00:04, 36.4MB/s]
8%|8 | 14.3M/170M [00:00<00:03, 42.4MB/s]
11%|# | 18.5M/170M [00:00<00:04, 38.1MB/s]
15%|#5 | 25.6M/170M [00:00<00:03, 48.5MB/s]
18%|#7 | 30.6M/170M [00:00<00:03, 47.0MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 48.0MB/s]
26%|##6 | 44.7M/170M [00:01<00:02, 46.4MB/s]
29%|##9 | 50.1M/170M [00:01<00:02, 45.7MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 45.6MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 46.7MB/s]
40%|#### | 68.5M/170M [00:01<00:02, 43.9MB/s]
46%|####6 | 78.3M/170M [00:01<00:01, 57.8MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 61.3MB/s]
54%|#####4 | 92.4M/170M [00:01<00:01, 55.4MB/s]
58%|#####7 | 98.0M/170M [00:02<00:01, 49.3MB/s]
61%|######1 | 104M/170M [00:02<00:01, 47.4MB/s]
66%|######5 | 112M/170M [00:02<00:01, 48.7MB/s
]
72%|#######2 | 123M/170M [00:02<00:00, 63.6MB/s]
76%|#######6 | 130M/170M [00:02<00:00, 63.9MB/s]
80%|######## | 136M/170M [00:02<00:00, 53.1MB/s]
85%|########4 | 144M/170M [00:02<00:00, 57.6MB/s]
88%|########8 | 150M/170M [00:03<00:00, 42.1MB/s]
93%|#########3| 158M/170M [00:03<00:00, 47.5MB/s]
96%|#########6| 164M/170M [00:03<00:00, 44.4MB/s]
99%|#########9| 168M/170M [00:03<00:00, 44.2MB/s]
100%|##########| 170M/170M [00:03<00:00, 49.1MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
1%|1 | 2.05M/170M [00:00<00:12, 14.0MB/s]
5%|4 | 7.99M/170M [00:00<00:04, 34.5MB/s]
9%|9 | 16.0M/170M [00:00<00:03, 43.7MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 48.6MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 55.8MB/s]
26%|##6 | 44.9M/170M [00:00<00:01, 77.6MB/s]
31%|###1 | 52.8M/170M [00:00<00:01, 71.9MB/s]
35%|###5 | 60.1M/170M [00:01<00:01, 68.4MB/s]
39%|###9 | 66.9M/170M [00:01<00:01, 61.0MB/s]
45%|####4 | 76.0M/170M [00:01<00:01, 69.4MB/s]
50%|####9 | 84.7M/170M [00:01<00:01, 75.2MB/s]
54%|#####4 | 92.2M/170M [00:01<00:01, 67.6MB/s]
58%|#####8 | 99.0M/170M [00:01<00:01, 44.3MB/s]
61%|######1 | 104M/170M [00:02<00:01, 43.6MB/s]
69%|######8 | 117M/170M [00:02<00:00, 61.6MB/s]
73%|#######3 | 124M/170M [00:02<00:00, 49.6MB/s]
77%|#######6 | 130M/170M [00:02<00:01, 40.3MB/s]
80%|######## | 136M/170M [00:02<00:00, 42.3MB/s]
83%|########3 | 141M/170M [00:02<00:00, 40.8MB/s]
86%|########5 | 146M/170M [00:02<00:00, 40.7MB/s]
89%|########9 | 152M/170M [00:03<00:00, 46.2MB/s]
94%|#########3| 159M/170M [00:03<00:00, 52.5MB/s]
99%|#########8| 168M/170M [00:03<00:00, 60.5MB/s]
100%|##########| 170M/170M [00:03<00:00, 53.9MB/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 22.469 seconds)
+ **Total running time of the script:** ( 3 minutes 28.341 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 2d4243312c..50eefb0f7a 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]
47%|####6 | 6.30M/13.6M [00:00<00:00, 45.4MB/s]
79%|#######8 | 10.6M/13.6M [00:00<00:00, 35.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 39.3MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 35.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 43.8MB/s]
@@ -409,7 +409,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 88.8823 88.8114 91.4137 88.5533 0.3346
+ 90.3648 90.2665 94.9289 90.1163 0.5225
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.248 seconds)
+ **Total running time of the script:** ( 1 minutes 16.271 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 3065808bab..40eb535d12 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)
- 114.8005 114.6520 118.6461 113.4900 0.9052
+ 121.1218 120.9935 125.8877 120.4494 0.6141
@@ -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 32.735 seconds)
+ **Total running time of the script:** ( 2 minutes 36.342 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized_tflite.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
index d01d525b28..2e1e53cb7d 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 45.123 seconds)
+ **Total running time of the script:** ( 1 minutes 42.188 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 4578acf4e8..fd0c6245dc 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]
4%|3 | 5306/132723 [00:00<00:02, 53048.04KB/s]
10%|9 | 12961/132723 [00:00<00:01, 66866.60KB/s]
15%|#4 | 19648/132723 [00:00<00:01, 64055.05KB/s]
21%|## | 27417/132723 [00:00<00:01, 69284.62KB/s]
26%|##5 | 34368/132723 [00:00<00:02, 48212.22KB/s]
32%|###1 | 42202/132723 [00:00<00:01, 56055.74KB/s]
38%|###7 | 50058/132723 [00:00<00:01, 62154.56KB/s]
44%|####3 | 57997/132723 [00:00<00:01, 66965.21KB/s]
50%|####9 | 65870/132723 [00:01<00:00, 70317.40KB/s]
55%|#####5 | 73636/132723 [00:01<00:00, 72438.14KB/s]
61%|######1 | 81402/132723 [00:01<00:00, 73962.69KB/s]
67%|######7 | 89186/132723 [00:01<00:00, 75102.87KB/s]
73%|#######3 | 96999/132723 [00:01<00:00, 75997.57KB/s]
79%|#######8 | 104753/132723 [00:01<00:00, 76452.52KB/s]
85%|########4 | 112537/132723 [00:01<00:00, 76843.32KB/s]
91%|#########
| 120355/132723 [00:01<00:00, 77240.05KB/s]
97%|#########6| 128214/132723 [00:01<00:00, 77641.98KB/s]
100%|##########| 132723/132723 [00:01<00:00, 70218.84KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4096/132723 [00:00<00:03, 40956.13KB/s]
10%|9 | 12773/132723 [00:00<00:01, 67894.94KB/s]
16%|#6 | 21495/132723 [00:00<00:01, 76714.42KB/s]
23%|##2 | 30099/132723 [00:00<00:01, 80393.11KB/s]
29%|##9 | 38706/132723 [00:00<00:01, 82435.85KB/s]
36%|###5 | 47450/132723 [00:00<00:01, 84127.53KB/s]
42%|####2 | 56109/132723 [00:00<00:00, 84929.91KB/s]
49%|####8 | 64874/132723 [00:00<00:00, 85785.43KB/s]
55%|#####5 | 73542/132723 [00:00<00:00, 86062.18KB/s]
62%|######1 | 82200/132723 [00:01<00:00, 86218.43KB/s]
68%|######8 | 90822/132723 [00:01<00:00, 86130.02KB/s]
75%|#######4 | 99436/132723 [00:01<00:00, 85168.29KB/s]
81%|########1 | 107956/132723 [00:01<00:00, 83901.06KB/s]
88%|########7 | 116663/132723 [00:01<00:00, 84839.67KB/s]
94%|#########4| 125303/132723 [00:01<00:00, 85303.41KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83144.71KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 37.296 seconds)
+ **Total running time of the script:** ( 3 minutes 45.869 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 8027e8a37b..a21b452b6e 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
=================
-**14:57.771** total execution time for **how_to_deploy_models** files:
+**15:20.582** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:37.296 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:45.869 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:22.469 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:28.341 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:32.735 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:36.342 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:45.123 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.188 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:12.248 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.271 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.374 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.380 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:39.490 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:41.012 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.205 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.783 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.826 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.390 | 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 5c81f6819d..84b6d174b8 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.zip4b0bf4fe-1e39-4a22-a4f7-5acdb7ca7803 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip4ef994b4-0c9d-4505-a33d-d1b12a530929 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 a19fc976ab..c3e0ba4a07 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
=================
-**00:51.465** total execution time for **how_to_extend_tvm** files:
+**00:54.229** 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``) | 00:47.822 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:50.364 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.609 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.758 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.098 | 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 aead3546ad..0d6e57263a 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: 22476us [22476us] (49.41%; 49.41%)
- FoldScaleAxis: 23015us [7us] (50.59%; 50.59%)
- FoldConstant: 23008us [1684us] (50.58%; 99.97%)
- InferType: 21324us [21324us] (46.87%; 92.68%)
+ InferType: 22349us [22349us] (48.77%; 48.77%)
+ FoldScaleAxis: 23473us [9us] (51.23%; 51.23%)
+ FoldConstant: 23463us [1745us] (51.21%; 99.96%)
+ InferType: 21718us [21718us] (47.40%; 92.56%)
@@ -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: 21143us [21143us] (48.25%; 48.25%)
- FoldScaleAxis: 22673us [5us] (51.75%; 51.75%)
- FoldConstant: 22668us [1603us] (51.73%; 99.98%)
- InferType: 21065us [21065us] (48.08%; 92.93%)
+ InferType: 21888us [21888us] (48.39%; 48.39%)
+ FoldScaleAxis: 23342us [6us] (51.61%; 51.61%)
+ FoldConstant: 23336us [1727us] (51.59%; 99.97%)
+ InferType: 21609us [21609us] (47.78%; 92.60%)
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 251ce6ef30..9eb3635d2b 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: 54.150718 ms
+ Convolution: 47.488960 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 20ce9dbcb5..cc988ee6b1 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: 9.267065 ms
+ conv2d with tensor core: 13.354188 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 aef3953196..ff91ddcce6 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: 0.017562
- Baseline: 3.256667
+ Numpy running time: 0.018650
+ Baseline: 3.225731
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.297628
+ Opt1: 0.312922
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.330059
+ Opt2: 0.340193
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.111028
+ Opt3: 0.122795
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.107514
+ Opt4: 0.109806
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110178
+ Opt5: 0.112097
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.143505
+ Opt6: 0.147239
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 5313721028..34aec35600 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.076** total execution time for **how_to_optimize_operators** files:
+**00:34.748** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.361 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.062 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.610 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.629 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.104 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.058 | 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 1d4aa6755e..0a495b8886 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
=================
-**09:37.615** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:08.840** 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``) | 05:57.833 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:20.417 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:37.847 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:41.535 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:05.698 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:08.426 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.164 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.109 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:13.281 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.016 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.793 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.336 | 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 20913453e1..78b03cc344 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
@@ -244,13 +244,13 @@ 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, 28)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([72], "float32", "shared")
+ T.launch_thread(blockIdx_x, 32)
+ conv2d_nchw = T.allocate([16], "float32", "local")
+ pad_temp_shared = T.allocate([4032], "float32", "shared")
kernel_shared = T.allocate([3072], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 64)
- conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
+ T.launch_thread(threadIdx_x, 49)
+ conv2d_nchw_1 = T.Buffer((16,), data=conv2d_nchw, scope="local")
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
@@ -265,460 +265,509 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = T.float32(0)
conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(64, 3):
- cse_var_2: T.int32 = rc_outer_outer * 72
- cse_var_1: T.int32 = ry_outer_outer * 3
+ conv2d_nchw_1[14] = T.float32(0)
+ conv2d_nchw_1[15] = T.float32(0)
+ for rc_outer_outer, rx_outer_outer in T.grid(8, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 3136
+ cse_var_1: T.int32 = rc_outer_outer * 576
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((72,), data=pad_temp_shared, scope="shared")
- with T.launch_thread(threadIdx_x_1, 64):
- data_1 = T.Buffer((25088,), data=data.data)
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 * 4 % 9 and threadIdx_x_1 * 4 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 * 4 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 * 4 % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 1) % 9 and (threadIdx_x_1 * 4 + 1) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 1) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 1) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 2] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 2) % 9 and (threadIdx_x_1 * 4 + 2) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 2) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 2) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 3] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 3) % 9 and (threadIdx_x_1 * 4 + 3) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 3) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1 = T.Buffer((4032,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 49) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 147) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 245] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 245) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 343] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 343) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 441] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 335], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 539] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 539) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 637] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 637) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 735] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 735) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 833] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 833) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 678], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 931] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 931) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1029] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1029) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1127] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1127) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1225] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1225) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1323] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 1021], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1421] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1421) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1519] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1519) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1617] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1617) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1715] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1715) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 1364], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1813] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1813) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1911] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1911) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2009] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2009) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2058] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2058) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2107] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2107) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2156] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2156) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2205] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 1707], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2254] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2254) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2303] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2303) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2352] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2352) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2401] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2401) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2450] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2450) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2499] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2499) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2548] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2548) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2597] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2597) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2646] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 2050], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2695] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2695) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2744] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2744) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2793] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2793) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2842] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2842) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2891] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2891) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2940] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2940) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2989] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2989) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3038] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3038) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3087] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 2393], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3136] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3136) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3185] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3185) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3234] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3234) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3283] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3283) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3332] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3332) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3381] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3381) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3430] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3430) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3479] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3479) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3528] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 2736], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3577] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3577) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3626] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3626) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3675] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3675) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3724] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3724) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3773] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3773) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3822] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3822) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3871] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3871) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3920] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3920) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3969] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 3079], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ if T.likely(threadIdx_x_1 < 14):
+ pad_temp_shared_1[threadIdx_x_1 + 4018] = T.if_then_else(threadIdx_x_1 < 7 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 4018) // 63 * 49 + rx_outer_outer + threadIdx_x_1 + 41], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
kernel_shared_1 = T.Buffer((3072,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 64) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 128) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 192] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 256) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 320) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 384] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 448) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 512) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 576] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 640) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 704) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 768] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 832) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 896) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 960] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1024) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1088) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1152] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1216) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1280) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1408) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1472) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1536] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 294912]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1600) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1664) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1728] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 331776]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1792) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1856) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1920] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 368640]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1984) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2048) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2112] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 405504]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2176) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2240) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2304] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 442368]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2368) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2432) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2496] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 479232]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2560) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2624) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 516096]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2752) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2816) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2880] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 552960]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2944) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 3008) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 47]
- for i1_inner, i3_inner in T.grid(2, 7):
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 49] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 147]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 294]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 147] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 147) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 147) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 12]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 245] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 245) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 159]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 306]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 343] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 343) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 151) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 392] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 24]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 441] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 441) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 171]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 490] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 318]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 539] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 539) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 155) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 588] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 588) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 36]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 637] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 637) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 183]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 686] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 686) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 330]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 735] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 735) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 159) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 48]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 833] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 833) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 195]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 882] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 882) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 342]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 931] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 931) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 163) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 980] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 980) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 60]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1029] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1029) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 207]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1078] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1078) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 354]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1127] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1127) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 167) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1176] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1176) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 72]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1225] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1225) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 219]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1274] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1274) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 366]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1323] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1323) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 171) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1372] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1372) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 84]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1421] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1421) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 231]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1470] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1470) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 378]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1519] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1519) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 175) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1568) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 96]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1617] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1617) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 243]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1666] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1666) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 390]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1715] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1715) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 179) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1764] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1764) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 108]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1813] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1813) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 255]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1862] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1862) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 402]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1911] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1911) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 183) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1960] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1960) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 120]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2009] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2009) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 267]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2058] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2058) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 414]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2107] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2107) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 187) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2156] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2156) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 132]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2205] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2205) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 279]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2254] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2254) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 426]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2303] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2303) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 191) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2352] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2352) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2401] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2401) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 291]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2450] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2450) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 146) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2499] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2499) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 9]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2548] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2548) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 156]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2597] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2597) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 303]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2646] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2646) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 150) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2695] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2695) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 21]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2744] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2744) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 168]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2793] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2793) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 315]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2842] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2842) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 154) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2891] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2891) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 33]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2940] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2940) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 180]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2989] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2989) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 327]
+ with T.launch_thread(threadIdx_x_2, 49):
+ if T.likely(threadIdx_x_2 < 34):
+ kernel_shared_1[threadIdx_x_2 + 3038] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 3038) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 474]
+ for rc_outer_inner in range(16):
+ cse_var_3: T.int32 = rc_outer_inner * 12
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 192]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 384]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 576]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 768]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 960]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1152]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1344]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1536]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1728]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1920]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2112]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2304]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2496]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2688]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2880]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 193]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 385]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 577]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 769]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 961]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1153]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1345]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1537]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1729]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1921]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2113]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2305]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2497]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2689]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2881]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 194]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 386]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 578]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 770]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 962]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1154]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1346]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1538]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1730]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1922]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2114]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2306]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2498]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2690]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2882]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 195]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 387]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 579]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 771]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 963]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1155]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1347]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1539]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1731]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1923]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2115]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2307]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2499]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2691]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2883]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 196]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 388]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 580]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 772]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 964]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1156]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1348]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1540]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1732]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1924]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2116]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2308]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2500]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2692]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2884]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 197]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 389]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 581]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 773]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 965]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1157]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1349]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1541]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1733]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1925]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2117]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2309]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2501]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2693]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2885]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 198]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 390]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 582]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 774]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 966]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1158]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1350]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1542]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1734]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1926]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2118]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2310]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2502]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2694]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2886]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 199]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 391]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 583]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 775]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 967]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1159]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1351]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1543]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1735]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1927]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2119]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2311]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2503]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2695]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2887]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 200]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 392]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 584]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 776]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 968]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1160]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1352]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1544]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1736]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1928]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2120]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2312]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2504]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2696]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2888]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 201]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 393]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 585]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 777]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 969]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1161]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1353]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1545]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1737]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1929]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2121]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2313]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2505]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2697]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2889]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 202]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 394]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 586]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 778]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 970]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1162]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1354]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1546]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1738]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1930]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2122]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2314]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2506]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2698]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2890]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 203]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 395]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 587]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 779]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 971]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1163]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1355]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1547]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1739]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1931]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2123]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2315]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2507]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2699]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2891]
+ for i1_inner in range(16):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x // 7 * 6272 + threadIdx_x * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + i1_inner], T.float32(0))
@@ -768,7 +817,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.361 ms
+ Execution time of this operator: 0.363 ms
@@ -816,36 +865,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=16)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_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=64)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -865,12 +914,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=4)
+ 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=64)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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, "unroll_explicit", True)
@@ -890,9 +939,9 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
+ 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[16];
+ __shared__ float pad_temp_shared[4032];
__shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -908,412 +957,360 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1707)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2050)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 3079)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 14) {
+ pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((int)threadIdx.x) < 7) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 63) * 49)) + rx_outer_outer) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 147)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 294)];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 147) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 147) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 245) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 159)];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 306)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 343) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 151) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 441) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 171)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 318)];
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 539) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 155) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 637) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 183)];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 330)];
+ kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 735) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 159) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 833)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 833) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 195)];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 342)];
+ kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 931) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 163) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 60)];
+ kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1029) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 207)];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 354)];
+ kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1127) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 167) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1225)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1225) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 219)];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 366)];
+ kernel_shared[(((int)threadIdx.x) + 1323)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1323) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 171) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 84)];
+ kernel_shared[(((int)threadIdx.x) + 1421)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1421) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 231)];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 378)];
+ kernel_shared[(((int)threadIdx.x) + 1519)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1519) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 175) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1617)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1617) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 243)];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 390)];
+ kernel_shared[(((int)threadIdx.x) + 1715)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1715) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 179) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 108)];
+ kernel_shared[(((int)threadIdx.x) + 1813)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1813) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 255)];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 402)];
+ kernel_shared[(((int)threadIdx.x) + 1911)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1911) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 183) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 120)];
+ kernel_shared[(((int)threadIdx.x) + 2009)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2009) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 267)];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 414)];
+ kernel_shared[(((int)threadIdx.x) + 2107)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2107) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 187) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 132)];
+ kernel_shared[(((int)threadIdx.x) + 2205)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2205) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 279)];
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 426)];
+ kernel_shared[(((int)threadIdx.x) + 2303)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2303) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 191) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 2401)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2401) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 291)];
+ kernel_shared[(((int)threadIdx.x) + 2450)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2450) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 146) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2499)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2499) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 9)];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 156)];
+ kernel_shared[(((int)threadIdx.x) + 2597)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2597) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 303)];
+ kernel_shared[(((int)threadIdx.x) + 2646)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2646) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 150) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2695)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2695) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 21)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 168)];
+ kernel_shared[(((int)threadIdx.x) + 2793)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2793) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 315)];
+ kernel_shared[(((int)threadIdx.x) + 2842)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2842) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 154) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2891)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2891) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 33)];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 180)];
+ kernel_shared[(((int)threadIdx.x) + 2989)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2989) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 327)];
+ if (((int)threadIdx.x) < 34) {
+ kernel_shared[(((int)threadIdx.x) + 3038)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3038) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 474)];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 64) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 128) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((((((int)threadIdx.x) + 256) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 320) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((((((int)threadIdx.x) + 448) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 512) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((((((int)threadIdx.x) + 640) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 704) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((((((int)threadIdx.x) + 832) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 896) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((((((int)threadIdx.x) + 1024) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1088) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((((((int)threadIdx.x) + 1216) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1280) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((((((int)threadIdx.x) + 1408) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1472) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((((((int)threadIdx.x) + 1600) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1664) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((((((int)threadIdx.x) + 1792) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1856) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((((((int)threadIdx.x) + 1984) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2048) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((((((int)threadIdx.x) + 2176) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2240) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((((((int)threadIdx.x) + 2368) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2432) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((((((int)threadIdx.x) + 2560) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2624) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((((((int)threadIdx.x) + 2752) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2816) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((((((int)threadIdx.x) + 2944) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 3008) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 192)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 384)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 768)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 960)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1152)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1344)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1536)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1728)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1920)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2112)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2304)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2496)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2688)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2880)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 193)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 385)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 577)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 769)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 961)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1153)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1345)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1537)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1729)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1921)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2113)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2305)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2497)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2689)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2881)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 194)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 386)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 770)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 962)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1154)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1346)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1538)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1730)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1922)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2114)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2306)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2498)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2690)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2882)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 195)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 387)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 579)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 771)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 963)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1155)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1347)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1539)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1731)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1923)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2115)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2307)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2499)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2691)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2883)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 196)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 388)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 580)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 772)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 964)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1156)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1348)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1540)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1732)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1924)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2116)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2308)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2500)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2692)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2884)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 197)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 389)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 773)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 965)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1157)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1349)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1541)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1733)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1925)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2117)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2309)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2501)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2693)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2885)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 198)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 390)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 582)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 774)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 966)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1158)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1350)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1542)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1734)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1926)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2118)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2310)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2502)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2694)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2886)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 199)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 391)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 583)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 775)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 967)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1159)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1351)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1543)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1735)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1927)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2119)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2311)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2503)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2695)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2887)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 200)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 392)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 776)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 968)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1160)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1352)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1544)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1736)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1928)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2120)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2312)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2504)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2696)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2888)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 201)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 393)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 777)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 969)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1161)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1353)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1545)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1737)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1929)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2121)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2313)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2505)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2697)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2889)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 202)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 394)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 586)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 778)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 970)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1162)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1354)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1546)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1738)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1930)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2122)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2314)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2506)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2698)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2890)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 203)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 395)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 779)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 971)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1163)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1355)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1547)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1739)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1931)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2123)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2315)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2507)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2699)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2891)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1373,7 +1370,7 @@ 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 57.833 seconds)
+ **Total running time of the script:** ( 6 minutes 20.417 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 4a61ca4916..868013d892 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)
- 7.9264 7.9225 7.9352 7.9216 0.0062
+ 7.9084 7.9097 7.9131 7.9023 0.0045
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.698 seconds)
+ **Total running time of the script:** ( 1 minutes 8.426 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 0e6c1bff5a..8553f277e9 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)
- 737.3005 734.2678 743.7643 733.8693 4.5735
+ 749.1448 748.3357 750.9397 748.1590 1.2712
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 37.847 seconds)
+ **Total running time of the script:** ( 1 minutes 41.535 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 da2dd7ec2f..f00973edf8 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
@@ -389,86 +389,27 @@ 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 in T.parallel(2):
- compute_1 = T.allocate([1024], "float32", "global")
- for i1_outer in range(32):
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_inner_init in range(64):
- cse_var_1: T.int32 = i_inner_init * 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(placeholder_5[i1_outer + 1] - placeholder_5[i1_outer], 64):
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- 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)
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_2: T.int32 = i_inner * 16
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_3: T.int32 = i_inner * 16 + 1
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 1] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_4: T.int32 = i_inner * 16 + 2
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 2] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_5: T.int32 = i_inner * 16 + 3
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 3] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_6: T.int32 = i_inner * 16 + 4
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 4] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_7: T.int32 = i_inner * 16 + 5
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 5] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_8: T.int32 = i_inner * 16 + 6
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 6] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_9: T.int32 = i_inner * 16 + 7
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 7] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_10: T.int32 = i_inner * 16 + 8
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 8] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_11: T.int32 = i_inner * 16 + 9
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 9] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_12: T.int32 = i_inner * 16 + 10
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 10] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_13: T.int32 = i_inner * 16 + 11
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 11] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_14: T.int32 = i_inner * 16 + 12
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 12] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_15: T.int32 = i_inner * 16 + 13
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 13] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_16: T.int32 = i_inner * 16 + 14
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 14] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_17: T.int32 = i_inner * 16 + 15
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 15] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- for i0_inner in range(64):
- cse_var_18: T.int32 = i0_outer * 32768 + i0_inner * 512 + i1_outer * 16
+ for i0_outer in T.parallel(32):
+ compute_1 = T.allocate([128], "float32", "global")
+ for i1_outer in range(16):
+ compute_2 = T.Buffer((128,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init, j_init in T.grid(4, 16):
+ compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i1_outer * 2 + nb_j_inner, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 4, 16):
+ cse_var_1 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_3: T.int32 = i1_outer * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(4):
+ cse_var_4: T.int32 = i0_outer * 2048 + i0_inner * 512 + i1_outer * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_18:cse_var_18 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_18:cse_var_18 + 16], T.Broadcast(T.float32(0), 16))
+ compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
@@ -518,7 +459,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.800 ms
+ Execution time of this operator: 1.276 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 0159a19186..8db793a30d 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:32.924** total execution time for **how_to_tune_with_autotvm** files:
+**00:52.317** 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``) | 00:32.891 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:52.284 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 1b9bd9ff9b..4a323ac5bd 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -390,7 +390,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9672678
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4128886
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -513,7 +513,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7612234
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7535911
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)
@@ -636,7 +636,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2799178
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9580633
No: 4 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)
@@ -759,9 +759,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6669761
- No: 5 GFLOPS: 6.64/6.64 result: MeasureResult(costs=(0.034884544249999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9321067333221436, timestamp=1677105940.151384) [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2527987
- No: 6 GFLOPS: 0.00/6.64 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2439798
+ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8618611
+ No: 6 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
@@ -883,9 +900,9 @@ 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, 4, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9414201
- No: 7 GFLOPS: 39.31/39.31 result: MeasureResult(costs=(0.005888479703703704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.340256690979004, timestamp=1677105941.1244223) [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7201636
- No: 8 GFLOPS: 0.00/39.31 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, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10124156
+ No: 7 GFLOPS: 35.64/35.64 result: MeasureResult(costs=(0.0064950799375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4253714084625244, timestamp=1677113892.7945414) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6432503
+ No: 8 GFLOPS: 0.00/35.64 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
@@ -1007,8 +1024,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8079014
- No: 9 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6696159
+ No: 9 GFLOPS: 0.00/35.64 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
@@ -1130,8 +1147,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1639059
- No: 10 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,528487
+ No: 10 GFLOPS: 0.00/35.64 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
@@ -1253,9 +1270,8 @@ 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, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9381190
- No: 11 GFLOPS: 1.76/39.31 result: MeasureResult(costs=(0.1316362915,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9758658409118652, timestamp=1677105944.317569) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,400679
- No: 12 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5261283
+ No: 11 GFLOPS: 0.00/35.64 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
@@ -1377,8 +1393,8 @@ 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, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7865712
- No: 13 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5067425
+ No: 12 GFLOPS: 0.00/35.64 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
@@ -1500,9 +1516,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4602651
- No: 14 GFLOPS: 9.04/39.31 result: MeasureResult(costs=(0.025608671,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1361608505249023, timestamp=1677105947.650252) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8987724
- No: 15 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9030182
+ No: 13 GFLOPS: 0.00/35.64 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
@@ -1624,8 +1639,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1150657
- No: 16 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8964907
+ No: 14 GFLOPS: 12.02/35.64 result: MeasureResult(costs=(0.01925196833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5436971187591553, timestamp=1677113901.3400843) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7758445
+ No: 15 GFLOPS: 12.20/35.64 result: MeasureResult(costs=(0.0189794985,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.47144341468811, timestamp=1677113902.2060459) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4727289
+ No: 16 GFLOPS: 0.00/35.64 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
@@ -1747,10 +1764,8 @@ 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5993857
- No: 17 GFLOPS: 50.74/50.74 result: MeasureResult(costs=(0.004562757636363637,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.40277099609375, timestamp=1677105949.255102) [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6781107
- No: 18 GFLOPS: 204.72/204.72 result: MeasureResult(costs=(0.0011308382808988763,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0636248588562012, timestamp=1677105949.9692926) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 7, 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', 0), ('unroll_explicit', 1)],None,5824450
- No: 19 GFLOPS: 0.00/204.72 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9714392
+ No: 17 GFLOPS: 0.00/35.64 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
@@ -1872,130 +1887,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7802662
- No: 20 GFLOPS: 0.00/204.72 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- 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:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- 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:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7308566
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6582345
+ No: 18 GFLOPS: 55.02/55.02 result: MeasureResult(costs=(0.0042074783,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.742863416671753, timestamp=1677113907.1546783) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10105368
+ No: 19 GFLOPS: 16.00/55.02 result: MeasureResult(costs=(0.014471026714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.590982437133789, timestamp=1677113907.9367762) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3098800
+ No: 20 GFLOPS: 50.97/55.02 result: MeasureResult(costs=(0.004541591782608695,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9592344760894775, timestamp=1677113908.6984577) [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6852641
@@ -2050,9 +1945,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 7, 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', 0), ('unroll_explicit', 1)],None,5824450
+ [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10105368
Finish loading 20 records
- Time cost of this operator: 0.001482
+ Time cost of this operator: 0.004236
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt
index 83a8da934e..70561a1213 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt
@@ -111,8 +111,8 @@ you need to export `TVM_MICRO_USE_HW` environment variable.
.. code-block:: default
- MODEL_URL = "https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/model/keyword_spotting_quant.tflite"
- MODEL_PATH = download_testdata(MODEL_URL, "keyword_spotting_quant.tflite", module="model")
+ MODEL_URL = "https://github.com/mlcommons/tiny/raw/bceb91c5ad2e2deb295547d81505721d3a87d578/benchmark/training/keyword_spotting/trained_models/kws_ref_model.tflite"
+ MODEL_PATH = download_testdata(MODEL_URL, "kws_ref_model.tflite", module="model")
SAMPLE_URL = "https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/data/keyword_spotting_int8_6.pyc.npy"
SAMPLE_PATH = download_testdata(SAMPLE_URL, "keyword_spotting_int8_6.pyc.npy", module="data")
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 49d1e0b46d..58f64f7d02 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 309.9 98.743 (1, 2, 10, 10, 3) 2 1 [309.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.951 0.94 (1, 6, 10, 10) 1 1 [2.951]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.994 0.317 (1, 1, 10, 10, 3) 1 1 [0.994]
- Total_time - 313.844 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.0 98.751 (1, 2, 10, 10, 3) 2 1 [317.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.04 0.947 (1, 6, 10, 10) 1 1 [3.04]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.302 (1, 1, 10, 10, 3) 1 1 [0.969]
+ Total_time - 321.009 - - - - -
@@ -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 133.6 98.071 (1, 6, 10, 10, 1) 2 1 [133.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.705 1.251 (1, 6, 10, 10) 1 1 [1.705]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.677 (1, 1, 10, 10, 3) 1 1 [0.923]
- Total_time - 136.227 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 137.5 98.056 (1, 6, 10, 10, 1) 2 1 [137.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.762 1.256 (1, 6, 10, 10) 1 1 [1.762]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.687 (1, 1, 10, 10, 3) 1 1 [0.964]
+ Total_time - 140.226 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.136 seconds)
+ **Total running time of the script:** ( 1 minutes 15.095 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index f56a64f99f..f223010e06 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, 144MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 10.9MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 17.2MB/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 10.276 seconds)
+ **Total running time of the script:** ( 1 minutes 14.077 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 505147bfd3..b9a37614c6 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/tmpbo72an5e/images/random'
+ '/tmp/tmp8i34xudc/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [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/tmpbo72an5e/images/target contains 8144 images
- /tmp/tmpbo72an5e/images/random contains 5000 images
+ /tmp/tmp8i34xudc/images/target contains 8144 images
+ /tmp/tmp8i34xudc/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 46s - loss: 0.2246 - accuracy: 0.9230 - val_loss: 0.1153 - val_accuracy: 0.9622 - 46s/epoch - 141ms/step
+ 328/328 - 47s - loss: 0.2288 - accuracy: 0.9205 - val_loss: 0.1645 - val_accuracy: 0.9418 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 42s - loss: 0.1061 - accuracy: 0.9602 - val_loss: 0.1102 - val_accuracy: 0.9630 - 42s/epoch - 129ms/step
+ 328/328 - 43s - loss: 0.1080 - accuracy: 0.9593 - val_loss: 0.0963 - val_accuracy: 0.9626 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 42s - loss: 0.0671 - accuracy: 0.9744 - val_loss: 0.1180 - val_accuracy: 0.9619 - 42s/epoch - 128ms/step
+ 328/328 - 43s - loss: 0.0722 - accuracy: 0.9723 - val_loss: 0.0731 - val_accuracy: 0.9739 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7f5f5a539450>
+ <keras.callbacks.History object at 0x7fcf124f9950>
@@ -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 38.407 seconds)
+ **Total running time of the script:** ( 4 minutes 52.569 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 1d19e6f345..939d01b4a3 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
=================
-**07:16.827** total execution time for **how_to_work_with_microtvm** files:
+**07:38.436** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:38.407 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:52.569 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:12.136 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:15.095 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:10.276 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:14.077 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.226 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.697 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:06.782 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:06.998 | 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 abbc90e39f..43542aaefb 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
=================
-**00:45.166** total execution time for **how_to_work_with_relay** files:
+**00:46.051** 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``) | 00:33.061 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.845 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.456 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.379 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.643 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.821 | 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 f8a0828e1e..86788d3804 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 0x7f5e07b20320>
+ <function my_cuda_math_rule at 0x7fcdbddff320>
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 e31f5f90ba..abe2a1ee07 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:07.500** total execution time for **how_to_work_with_schedules** files:
+**00:08.217** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.947 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.509 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.183 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.284 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.584 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.621 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.573 | 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_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.053 | 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``) | 00:00.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 97ee7ddfd5..100eae7791 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
=================
-**00:29.480** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:31.351** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:29.473 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.345 | 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 0f45fb4a0c..72fd239c29 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 31.33s!
+ resnet18_v1 inference graph built in 33.46s!
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 10bed15219..6f2b33b36c 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 21.44s!
+ yolov3-tiny inference graph built in 22.59s!
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 ad4204e9b4..7df618c39f 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
=================
-**01:36.317** total execution time for **topic_vta_tutorials_frontend** files:
+**01:39.975** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.354 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.322 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.964 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.653 | 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 a7eabad843..b5ff8cb3ff 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
=================
-**00:03.197** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.229** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.722 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.770 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.475 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.460 | 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 fa744f923d..68f0f74eb0 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
=================
-**00:00.799** total execution time for **topic_vta_tutorials** files:
+**00:00.785** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.415 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.406 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.385 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.378 | 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 93964ce569..382f9baee5 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -318,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 96.918 ms
+ Execution time of this operator: 94.658 ms
@@ -434,7 +434,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.996 seconds)
+ **Total running time of the script:** ( 1 minutes 15.766 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 fc133b146f..5dbfed5db3 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: 1.33/1.33 result: MeasureResult(costs=(0.20150971239999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4580695629119873, timestamp=1677104413.5371518) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
- No: 2 GFLOPS: 10.17/10.17 result: MeasureResult(costs=(0.026402166999999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6663382053375244, timestamp=1677104415.2317772) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 3 GFLOPS: 1.57/10.17 result: MeasureResult(costs=(0.1705915238,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9561731815338135, timestamp=1677104418.21246) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
- No: 4 GFLOPS: 11.47/11.47 result: MeasureResult(costs=(0.0234092124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5987229347229004, timestamp=1677104419.8494754) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
- No: 5 GFLOPS: 12.93/12.93 result: MeasureResult(costs=(0.0207674204,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5837922096252441, timestamp=1677104420.570474) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
- No: 6 GFLOPS: 13.93/13.93 result: MeasureResult(costs=(0.0192654652,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5707182884216309, timestamp=1677104421.127512) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
- No: 7 GFLOPS: 2.10/13.93 result: MeasureResult(costs=(0.1275663182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.265695571899414, timestamp=1677104424.4246516) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
- No: 8 GFLOPS: 10.54/13.93 result: MeasureResult(costs=(0.0254767484,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6514315605163574, timestamp=1677104425.0843453) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
- No: 9 GFLOPS: 11.96/13.93 result: MeasureResult(costs=(0.0224537488,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5848391056060791, timestamp=1677104425.7839394) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
- No: 10 GFLOPS: 2.72/13.93 result: MeasureResult(costs=(0.0987381366,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7782678604125977, timestamp=1677104427.612232) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
+ No: 1 GFLOPS: 10.40/10.40 result: MeasureResult(costs=(0.025814362999999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6747267246246338, timestamp=1677112316.5368395) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+ No: 2 GFLOPS: 0.44/10.40 result: MeasureResult(costs=(0.6063898632000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.929502248764038, timestamp=1677112326.4930599) [('tile_y', [-1, 512]), ('tile_x', [-1, 1])],None,9
+ No: 3 GFLOPS: 12.34/12.34 result: MeasureResult(costs=(0.021761731200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6748085021972656, timestamp=1677112328.1477122) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
+ No: 4 GFLOPS: 1.35/12.34 result: MeasureResult(costs=(0.1987207044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.3973758220672607, timestamp=1677112332.6285071) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
+ No: 5 GFLOPS: 1.66/12.34 result: MeasureResult(costs=(0.16127901579999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8095438480377197, timestamp=1677112335.5909843) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 6 GFLOPS: 9.18/12.34 result: MeasureResult(costs=(0.029252762199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7144911289215088, timestamp=1677112336.311804) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+ No: 7 GFLOPS: 11.50/12.34 result: MeasureResult(costs=(0.0233467048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6326639652252197, timestamp=1677112337.9784367) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
+ No: 8 GFLOPS: 12.35/12.35 result: MeasureResult(costs=(0.0217334368,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6160697937011719, timestamp=1677112338.5884128) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
+ No: 9 GFLOPS: 3.59/12.35 result: MeasureResult(costs=(0.07477229760000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.423443078994751, timestamp=1677112340.1246536) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 10 GFLOPS: 3.25/12.35 result: MeasureResult(costs=(0.0825876108,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5303704738616943, timestamp=1677112341.6964521) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index eba57cf184..3064c87379 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': 498.81961337999775, 'median': 498.59456844999386, 'std': 1.129652498706445}
+ {'mean': 511.6213232799999, 'median': 510.78641235000646, 'std': 2.559396471416024}
@@ -545,31 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 10.96/ 18.08 GFLOPS | Progress: (4/20) | 8.59 s
[Task 1/25] Current/Best: 6.47/ 23.63 GFLOPS | Progress: (8/20) | 12.80 s
[Task 1/25] Current/Best: 18.08/ 23.63 GFLOPS | Progress: (12/20) | 16.33 s
[Task 1/25] Current/Best: 12.69/ 23.63 GFLOPS | Progress: (16/20) | 20.24 s
[Task 1/25] Current/Best: 18.12/ 23.63 GFLOPS | Progress: (20/20) | 22.21 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 14.54/ 16.70 GFLOPS | Progress: (4/20) | 4.78 s
[Task 2/25] Current/Best: 12.23/ 17.89 GFLOPS | Progress: (8/20) | 6.27 s
[Task 2/25] Current/Best: 14.48/ 17.89 GFLOPS | Progress: (12/20) | 8.10 s
[Task 2/25] Current/Best: 13.21/ 19.94 GFLOPS | Progress: (16/20) | 9.58 s
[Task 2/25] Current/Best: 7.01/ 19.94 GFLOPS | Progress: (20/20) | 11.26 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 3.17/ 22.93 GFLOPS | Progress: (4/20) | 5.03 s
[Task 3/25] Current/Best: 12.74/ 22.93 GFLOPS | Progress: (8/20) | 7.57 s
[Task 3/25] Current/Best: 9.52/ 23.65 GFLOPS | Progress: (12/20) | 9.94 s
[Task 3/25] Current/Best: 1.65/ 23.65 GFLOPS | Progress: (16/20) | 14.92 s
[Task 3/25] Current/Best: 11.93/ 23.65 GFLOPS | Progress: (20/20) | 17.16 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 8.84/ 12.68 GFLOPS | Progress: (4/20) | 5.74 s
[Task 4/25] Current/Best: 12.27/ 13.91 GFLOPS | Progress: (8/20) | 9.11 s
[Task 4/25] Current/Best: 16.00/ 17.19 GFLOPS | Progress: (12/20) | 11.23 s
[Task 4/25] Current/Best: 16.89/ 17.19 GFLOPS | Progress: (16/20) | 14.17 s
[Task 4/25] Current/Best: 11.15/ 17.19 GFLOPS | Progress: (20/20) | 16.37 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 4.76/ 22.34 GFLOPS | Progress: (4/20) | 4.68 s
[Task 5/25] Current/Best: 5.06/ 22.34 GFLOPS | Progress: (8/20) | 7.32 s
[Task 5/25] Current/Best: 11.92/ 22.34 GFLOPS | Progress: (12/20) | 9.54 s
[Task 5/25] Current/Best: 5.45/ 22.34 GFLOPS | Progress: (16/20) | 11.52 s
[Task 5/25] Current/Best: 21.16/ 22.34 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: 15.16/ 17.41 GFLOPS | Progress: (4/20) | 4.98 s
[Task 6/25] Current/Best: 11.51/ 17.41 GFLOPS | Progress: (8/20) | 10.44 s
[Task 6/25] Current/Best: 1.35/ 17.41 GFLOPS | Progress: (12/20) | 14.47 s
[Task 6/25] Current/Best: 8.70/ 17.41 GFLOPS | Progress: (16/20) | 18.17 s
[Task 6/25] Current/Best: 12.73/ 21.54 GFLOPS | Progress: (20/20) | 20.87 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.03/ 18.85 GFLOPS | Progress: (4/20) | 5.33 s
[Task 7/25] Current/Best: 18.76/ 18.85 GFLOPS | Progress: (8/20) | 7.59 s
[Task 7/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (12/20) | 9.79 s
[Task 7/25] Current/Best: 3.14/ 19.95 GFLOPS | Progress: (16/20) | 13.00 s
[Task 7/25] Current/Best: 22.84/ 22.84 GFLOPS | Progress: (20/20) | 15.43 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.17/ 21.19 GFLOPS | Progress: (4/20) | 5.16 s
[Task 8/25] Current/Best: 13.38/ 21.19 GFLOPS | Progress: (8/20) | 9.52 s
[Task 8/25] Current/Best: 19.35/ 21.19 GFLOPS | Progress: (12/20) | 11.67 s
[Task 8/25] Current/Best: 16.16/ 21.19 GFLOPS | Progress: (16/20) | 14.65 s
[Task 8/25] Current/Best: 13.77/ 21.29 GFLOPS | Progress: (20/20) | 17.07 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 12.40/ 17.70 GFLOPS | Progress: (4/20) | 4.87 s
[Task 9/25] Current/Best: 15.39/ 17.70 GFLOPS | Progress: (8/20) | 11.15 s
[Task 9/25] Current/Best: 8.68/ 17.70 GFLOPS | Progress: (12/20) | 13.39 s
[Task 9/25] Current/Best: 10.91/ 18.36 GFLOPS | Progress: (16/20) | 19.36 s
[Task 9/25] Current/Best: 10.20/ 19.64 GFLOPS | Progress: (20/20) | 25.57 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.98/ 12.98 GFLOPS | Progress: (4/20) | 5.86 s
[Task 10/25] Current/Best: 2.90/ 12.98 GFLOPS | Progress: (8/20) | 9.86 s
[Task 10/25] Current/Best: 13.54/ 17.29 GFLOPS | Progress: (12/20) | 11.69 s
[Task 10/25] Current/Best: 9.24/ 17.29 GFLOPS | Progress: (16/20) | 14.68 s
[Task 10/25] Current/Best: 4.90/ 17.29 GFLOPS | Progress: (20/20) | 16.70 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.08/ 17.84 GFLOPS | Progress: (4/20) | 5.23 s
[Task 11/25] Current/Best: 6.82/ 18.87 GFLOPS | Progress: (8/20) | 7.99 s
[Task 11/25] Current/Best: 10.41/ 18.87 GFLOPS | Progress: (12/20) | 10.62 s
[Task 11/25] Current/Best: 22.78/ 22.78 GFLOPS | Progress: (16/20) | 13.12 s
[Task 11/25] Current/Best: 16.87/ 22.78 GFLOPS | Progress: (20/20) | 16.05 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.46/ 16.68 GFLOPS | Progress: (4/20) | 6.15 s
[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (8/20) | 9.12 s
[Task 12/25] Current/Best: 18.51/ 18.95 GFLOPS | Progress: (12/20) | 12.79 s
[Task 12/25] Current/Best: 10.39/ 18.95 GFLOPS | Progress: (16/20) | 17.32 s
[Task 12/25] Current/Best: 3.32/ 18.95 GFLOPS | Progress: (20/20) | 21.50 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (4/20) | 5.46 s
[Task 13/25] Current/Best: 11.71/ 19.71 GFLOPS | Progress: (8/20) | 9.38 s
[Task 13/25] Current/Best: 12.11/ 19.71 GFLOPS | Progress: (12/20) | 13.07 s
[Task 13/25] Current/Best: 8.80/ 19.71 GFLOPS | Progress: (16/20) | 16.05 s
[Task 13/25] Current/Best: 14.19/ 19.71 GFLOPS | Progress: (20/20) | 18.52 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.22/ 14.19 GFLOPS | Progress: (4/20) | 5.22 s
[Task 14/25] Current/Best: 9.45/ 21.02 GFLOPS | Progress: (8/20) | 8.91 s
[Task 14/25] Current/Best: 12.86/ 21.02 GFLOPS | Progress: (12/20) | 12.21 s
[Task 14/25] Current/Best: 11.75/ 21.02 GFLOPS | Progress: (16/20) | 15.16 s
[Task 14/25] Current/Best: 13.10/ 21.02 GFLOPS | Progress: (20/20) | 18.52 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 8.18/ 19.98 GFLOPS | Progress: (4/20) | 7.24 s
[Task 15/25] Current/Best: 11.11/ 19.98 GFLOPS | Progress: (8/20) | 8.90 s
[Task 15/25] Current/Best: 13.96/ 22.48 GFLOPS | Progress: (12/20) | 10.78 s
[Task 15/25] Current/Best: 20.04/ 23.07 GFLOPS | Progress: (16/20) | 13.52 s
[Task 15/25] Current/Best: 10.24/ 23.07 GFLOPS | Progress: (20/20
) | 16.66 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 15.35/ 15.35 GFLOPS | Progress: (4/20) | 5.04 s
[Task 16/25] Current/Best: 6.09/ 22.24 GFLOPS | Progress: (8/20) | 6.97 s
[Task 16/25] Current/Best: 7.67/ 22.24 GFLOPS | Progress: (12/20) | 8.56 s
[Task 16/25] Current/Best: 13.47/ 22.24 GFLOPS | Progress: (16/20) | 10.48 s
[Task 16/25] Current/Best: 14.84/ 22.24 GFLOPS | Progress: (20/20) | 12.13 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/20) | 7.20 s
[Task 17/25] Current/Best: 11.94/ 22.26 GFLOPS | Progress: (8/20) | 10.46 s
[Task 17/25] Current/Best: 1.58/ 22.26 GFLOPS | Progress: (12/20) | 14.36 s
[Task 17/25] Current/Best: 17.89/ 22.26 GFLOPS | Progress: (16/20) | 17.00 s
[Task 17/25] Current/Best: 16.84/ 22.26 GFLOPS | Progress: (20/20) | 20.61 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 12.49/ 17.21 GFLOPS | Progress: (4/20) | 8.64 s
[Task 18/25] Current/Best: 6.61/ 17.21 GFLOPS | Progress: (8/20) | 12.74 s
[Task 18/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (12/20) | 19.89 s
[Task 18/25] Current/Best: 11.69/ 19.58 GFLOPS | Progress: (16/20) | 22.75 s
[Task 18/25] Current/Best: 8.39/ 19.58 GFLOPS | Progress: (20/20) | 24.75 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.27/ 18.79 GFLOPS | Progress: (4/20) | 5.65 s
[Task 19/25] Current/Best: 11.16/ 18.79 GFLOPS | Progress: (8/20) | 9.12 s
[Task 19/25] Current/Best: 19.75/ 19.75 GFLOPS | Progress: (12/20) | 11.32 s
[Task 19/25] Current/Best: 16.64/ 19.75 GFLOPS | Progress: (16/20) | 14.89 s
[Task 19/25] Current/Best: 17.10/ 19.75 GFLOPS | Progress: (20/20) | 18.45 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 6.74/ 17.96 GFLOPS | Progress: (4/20) | 4.34 s
[Task 20/25] Current/Best: 6.29/ 17.96 GFLOPS | Progress: (8/20) | 8.37 s
[Task 20/25] Current/Best: 12.01/ 17.96 GFLOPS | Progress: (12/20) | 11.38 s
[Task 20/25] Current/Best: 17.86/ 17.96 GFLOPS | Progress: (16/20) | 14.27 s
[Task 20/25] Current/Best: 10.98/ 17.96 GFLOPS | Progress: (20/20) | 17.46 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 21/25] Current/Best: 14.26/ 21.17 GFLOPS | Progress: (4/20) | 5.30 s
[Task 21/25] Current/Best: 10.13/ 21.17 GFLOPS | Progress: (8/20) | 7.19 s
[Task 21/25] Current/Best: 9.08/ 21.17 GFLOPS | Progress: (12/20) | 9.73 s
[Task 21/25] Current/Best: 11.15/ 21.17 GFLOPS | Progress: (16/20) | 11.43 s
[Task 21/25] Current/Best: 20.81/ 21.76 GFLOPS | Progress: (20/20) | 14.11 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.15/ 15.15 GFLOPS | Progress: (4/20) | 7.16 s
[Task 22/25] Current/Best: 9.34/ 15.15 GFLOPS | Progress: (8/20) | 8.96 s
[Task 22/25] Current/Best: 18.24/ 19.02 GFLOPS | Progress: (12/20) | 10.94 s
[Task 22/25] Current/Best: 10.95/ 19.02 GFLOPS | Progress: (16/20) | 12.73 s
[Task 22/25] Current/Best: 9.78/ 19.02 GFLOPS | Progress: (20/20) | 15.30 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 20.60/ 22.05 GFLOPS | Progress: (4/20) | 4.62 s
[Task 23/25] Current/Best: 17.88/ 22.05 GFLOPS | Progress: (8/20) | 7.65 s
[Task 23/25] Current/Best: 12.45/ 22.05 GFLOPS | Progress: (12/20) | 10.71 s
[Task 23/25] Current/Best: 17.89/ 22.05 GFLOPS | Progress: (16/20) | 13.79 s
[Task 23/25] Current/Best: 12.58/ 22.05 GFLOPS | Progress: (20/20) | 17.00 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.06/ 10.80 GFLOPS | Progress: (4/20) | 4.71 s
[Task 24/25] Current/Best: 7.88/ 10.80 GFLOPS | Progress: (8/20) | 15.62 s
[Task 24/25] Current/Best: 7.65/ 10.80 GFLOPS | Progress: (12/20) | 17.97 s
[Task 24/25] Current/Best: 3.94/ 10.80 GFLOPS | Progress: (16/20) | 26.53 s
[Task 24/25] Current/Best: 5.88/ 10.80 GFLOPS | Progress: (20/20) | 38.75 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 6.34/ 15.34 GFLOPS | Progress: (4/20) | 11.61 s
[Task 1/25] Current/Best: 16.27/ 16.27 GFLOPS | Progress: (8/20) | 15.01 s
[Task 1/25] Current/Best: 15.06/ 17.44 GFLOPS | Progress: (12/20) | 19.11 s
[Task 1/25] Current/Best: 21.49/ 21.49 GFLOPS | Progress: (16/20) | 21.49 s
[Task 1/25] Current/Best: 8.44/ 21.49 GFLOPS | Progress: (20/20) | 25.39 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 10.25/ 17.32 GFLOPS | Progress: (4/20) | 4.43 s
[Task 2/25] Current/Best: 10.03/ 20.10 GFLOPS | Progress: (8/20) | 6.13 s
[Task 2/25] Current/Best: 6.37/ 20.10 GFLOPS | Progress: (12/20) | 9.53 s
[Task 2/25] Current/Best: 16.75/ 20.10 GFLOPS | Progress: (16/20) | 10.96 s
[Task 2/25] Current/Best: 9.91/ 20.10 GFLOPS | Progress: (20/20) | 12.63 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.34/ 15.34 GFLOPS | Progress: (4/20) | 5.19 s
[Task 3/25] Current/Best: 19.22/ 19.22 GFLOPS | Progress: (8/20) | 8.96 s
[Task 3/25] Current/Best: 13.73/ 21.32 GFLOPS | Progress: (12/20) | 10.95 s
[Task 3/25] Current/Best: 18.28/ 21.32 GFLOPS | Progress: (16/20) | 13.91 s
[Task 3/25] Current/Best: 15.13/ 21.32 GFLOPS | Progress: (20/20) | 16.51 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 14.20/ 14.20 GFLOPS | Progress: (4/20) | 4.51 s
[Task 4/25] Current/Best: 11.16/ 14.99 GFLOPS | Progress: (8/20) | 6.95 s
[Task 4/25] Current/Best: 9.99/ 16.05 GFLOPS | Progress: (12/20) | 18.27 s
[Task 4/25] Current/Best: 12.20/ 16.05 GFLOPS | Progress: (16/20) | 21.90 s
[Task 4/25] Current/Best: 15.10/ 16.05 GFLOPS | Progress: (20/20) | 26.73 s
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 5/25] Current/Best: 4.70/ 12.80 GFLOPS | Progress: (4/20) | 4.79 s
[Task 5/25] Current/Best: 3.92/ 17.62 GFLOPS | Progress: (8/20) | 7.29 s
[Task 5/25] Current/Best: 12.62/ 17.62 GFLOPS | Progress: (12/20) | 9.70 s
[Task 5/25] Current/Best: 11.01/ 17.62 GFLOPS | Progress: (16/20) | 12.25 s
[Task 5/25] Current/Best: 11.44/ 17.62 GFLOPS | Progress: (20/20) | 14.95 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 9.50/ 18.53 GFLOPS | Progress: (4/20) | 4.89 s
[Task 6/25] Current/Best: 11.13/ 18.53 GFLOPS | Progress: (8/20) | 8.05 s
[Task 6/25] Current/Best: 5.98/ 20.14 GFLOPS | Progress: (12/20) | 10.57 s
[Task 6/25] Current/Best: 5.46/ 20.14 GFLOPS | Progress: (16/20) | 14.11 s
[Task 6/25] Current/Best: 11.05/ 20.14 GFLOPS | Progress: (20/20) | 17.13 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.55/ 12.84 GFLOPS | Progress: (4/20) | 5.16 s
[Task 7/25] Current/Best: 6.29/ 18.54 GFLOPS | Progress: (8/20) | 7.72 s
[Task 7/25] Current/Best: 13.22/ 18.54 GFLOPS | Progress: (12/20) | 10.00 s
[Task 7/25] Current/Best: 14.54/ 18.54 GFLOPS | Progress: (16/20) | 12.24 s
[Task 7/25] Current/Best: 18.56/ 18.56 GFLOPS | Progress: (20/20) | 15.32 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 20.02/ 20.02 GFLOPS | Progress: (4/20) | 5.40 s
[Task 8/25] Current/Best: 13.99/ 22.20 GFLOPS | Progress: (8/20) | 8.36 s
[Task 8/25] Current/Best: 7.04/ 22.20 GFLOPS | Progress: (12/20) | 13.91 s
[Task 8/25] Current/Best: 12.14/ 22.20 GFLOPS | Progress: (16/20) | 16.90 s
[Task 8/25] Current/Best: 5.65/ 22.20 GFLOPS | Progress: (20/20) | 26.21 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.58/ 18.80 GFLOPS | Progress: (4/20) | 6.13 s
[Task 9/25] Current/Best: 9.96/ 18.80 GFLOPS | Progress: (8/20) | 17.34 s
[Task 9/25] Current/Best: 6.20/ 19.22 GFLOPS | Progress: (12/20) | 23.74 s
[Task 9/25] Current/Best: 11.91/ 19.22 GFLOPS | Progress: (16/20) | 26.00 s
[Task 9/25] Current/Best: 15.38/ 19.22 GFLOPS | Progress: (20/20) | 28.03 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 8.94/ 15.79 GFLOPS | Progress: (4/20) | 5.35 s
[Task 10/25] Current/Best: 6.44/ 18.08 GFLOPS | Progress: (8/20) | 7.47 s
[Task 10/25] Current/Best: 11.72/ 18.18 GFLOPS | Progress: (12/20) | 11.07 s
[Task 10/25] Current/Best: 5.91/ 18.18 GFLOPS | Progress: (16/20) | 13.43 s
[Task 10/25] Current/Best: 9.95/ 18.18 GFLOPS | Progress: (20/2
0) | 15.34 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 17.74/ 19.45 GFLOPS | Progress: (4/20) | 4.23 s
[Task 11/25] Current/Best: 18.22/ 19.45 GFLOPS | Progress: (8/20) | 6.53 s
[Task 11/25] Current/Best: 21.27/ 22.52 GFLOPS | Progress: (12/20) | 8.90 s
[Task 11/25] Current/Best: 10.95/ 22.52 GFLOPS | Progress: (16/20) | 11.35 s
[Task 11/25] Current/Best: 11.14/ 22.52 GFLOPS | Progress: (20/20) | 15.43 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 12.83/ 17.57 GFLOPS | Progress: (4/20) | 5.53 s
[Task 12/25] Current/Best: 14.64/ 17.57 GFLOPS | Progress: (8/20) | 8.67 s
[Task 12/25] Current/Best: 17.96/ 18.18 GFLOPS | Progress: (12/20) | 10.86 s
[Task 12/25] Current/Best: 17.73/ 18.18 GFLOPS | Progress: (16/20) | 14.41 s
[Task 12/25] Current/Best: 6.80/ 18.18 GFLOPS | Progress: (20/20) | 18.04 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 19.82/ 19.82 GFLOPS | Progress: (4/20) | 6.15 s
[Task 13/25] Current/Best: 6.46/ 19.82 GFLOPS | Progress: (8/20) | 9.50 s
[Task 13/25] Current/Best: 15.46/ 19.82 GFLOPS | Progress: (12/20) | 12.84 s
[Task 13/25] Current/Best: 13.30/ 19.88 GFLOPS | Progress: (16/20) | 15.99 s
[Task 13/25] Current/Best: 15.50/ 19.88 GFLOPS | Progress: (20/20) | 18.85 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.18/ 12.18 GFLOPS | Progress: (4/20) | 6.33 s
[Task 14/25] Current/Best: 10.62/ 19.63 GFLOPS | Progress: (8/20) | 8.46 s
[Task 14/25] Current/Best: 13.96/ 19.63 GFLOPS | Progress: (12/20) | 11.32 s
[Task 14/25] Current/Best: 18.46/ 19.63 GFLOPS | Progress: (16/20) | 13.17 s
[Task 14/25] Current/Best: 9.93/ 19.63 GFLOPS | Progress: (20/20) | 17.56 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 9.39/ 14.08 GFLOPS | Progress: (4/20) | 9.64 s
[Task 15/25] Current/Best: 13.43/ 14.08 GFLOPS | Progress: (8/20) | 15.58 s
[Task 15/25] Current/Best: 17.80/ 17.80 GFLOPS | Progress: (12/20) | 21.05 s
[Task 15/25] Current/Best: 13.26/ 17.80 GFLOPS | Progress: (16/20) | 23.40 s Done.
Done.
- Done.
- Done.
-
[Task 25/25] Current/Best: 5.46/ 5.46 GFLOPS | Progress: (4/20) | 6.82 s
[Task 25/25] Current/Best: 10.34/ 10.34 GFLOPS | Progress: (8/20) | 9.84 s
[Task 25/25] Current/Best: 6.64/ 10.34 GFLOPS | Progress: (12/20) | 20.75 s
[Task 25/25] Current/Best: 1.58/ 10.34 GFLOPS | Progress: (16/20) | 25.76 s
[Task 25/25] Current/Best: 9.24/ 10.34 GFLOPS | Progress: (20/20) | 28.15 s
+
[Task 15/25] Current/Best: 3.13/ 17.80 GFLOPS | Progress: (20/20) | 26.50 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.93/ 16.93 GFLOPS | Progress: (4/20) | 6.47 s
[Task 16/25] Current/Best: 14.43/ 16.93 GFLOPS | Progress: (8/20) | 9.22 s
[Task 16/25] Current/Best: 15.10/ 16.93 GFLOPS | Progress: (12/20) | 11.33 s
[Task 16/25] Current/Best: 3.04/ 20.36 GFLOPS | Progress: (16/20) | 14.52 s
[Task 16/25] Current/Best: 15.52/ 20.36 GFLOPS | Progress: (20/20) | 16.06 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.65/ 17.04 GFLOPS | Progress: (4/20) | 6.06 s
[Task 17/25] Current/Best: 17.71/ 18.72 GFLOPS | Progress: (8/20) | 9.12 s
[Task 17/25] Current/Best: 13.85/ 18.72 GFLOPS | Progress: (12/20) | 12.78 s
[Task 17/25] Current/Best: 1.56/ 20.83 GFLOPS | Progress: (16/20) | 16.65 s
[Task 17/25] Current/Best: 6.21/ 23.69 GFLOPS | Progress: (20/20) | 19.44 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 13.86/ 17.36 GFLOPS | Progress: (4/20) | 6.12 s
[Task 18/25] Current/Best: 11.73/ 19.22 GFLOPS | Progress: (8/20) | 9.25 s
[Task 18/25] Current/Best: 14.43/ 19.22 GFLOPS | Progress: (12/20) | 11.08 s
[Task 18/25] Current/Best: 17.01/ 19.22 GFLOPS | Progress: (16/20) | 13.26 s
[Task 18/25] Current/Best: 7.06/ 19.22 GFLOPS | Progress: (20/20) | 15.37 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 13.34/ 21.75 GFLOPS | Progress: (4/20) | 5.21 s
[Task 19/25] Current/Best: 13.34/ 21.75 GFLOPS | Progress: (8/20) | 8.19 s
[Task 19/25] Current/Best: 7.97/ 21.75 GFLOPS | Progress: (12/20) | 13.27 s
[Task 19/25] Current/Best: 10.01/ 21.75 GFLOPS | Progress: (16/20) | 16.19 s
[Task 19/25] Current/Best: 8.15/ 21.75 GFLOPS | Progress: (20/20) | 20.02 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.30/ 10.30 GFLOPS | Progress: (4/20) | 5.77 s
[Task 20/25] Current/Best: 15.05/ 19.88 GFLOPS | Progress: (8/20) | 9.34 s
[Task 20/25] Current/Best: 12.31/ 19.88 GFLOPS | Progress: (12/20) | 11.96 s
[Task 20/25] Current/Best: 14.94/ 19.88 GFLOPS | Progress: (16/20) | 14.52 s
[Task 20/25] Current/Best: 10.15/ 19.88 GFLOPS | Progress: (20/20) | 17.43 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 10.67/ 18.03 GFLOPS | Progress: (4/20) | 6.01 s
[Task 21/25] Current/Best: 19.82/ 19.82 GFLOPS | Progress: (8/20) | 10.71 s
[Task 21/25] Current/Best: 5.36/ 19.82 GFLOPS | Progress: (12/20) | 13.57 s Done.
+
[Task 21/25] Current/Best: 17.24/ 19.82 GFLOPS | Progress: (16/20) | 16.18 s
[Task 21/25] Current/Best: 9.31/ 20.18 GFLOPS | Progress: (20/20) | 17.84 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 11.63/ 18.31 GFLOPS | Progress: (4/20) | 4.33 s
[Task 22/25] Current/Best: 10.12/ 18.31 GFLOPS | Progress: (8/20) | 6.92 s
[Task 22/25] Current/Best: 15.40/ 18.31 GFLOPS | Progress: (12/20) | 8.84 s
[Task 22/25] Current/Best: 10.44/ 18.31 GFLOPS | Progress: (16/20) | 12.68 s
[Task 22/25] Current/Best: 10.66/ 18.31 GFLOPS | Progress: (20/20) | 15.61 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.71/ 16.83 GFLOPS | Progress: (4/20) | 5.04 s
[Task 23/25] Current/Best: 14.63/ 16.83 GFLOPS | Progress: (8/20) | 9.69 s
[Task 23/25] Current/Best: 12.38/ 20.40 GFLOPS | Progress: (12/20) | 13.83 s
[Task 23/25] Current/Best: 9.73/ 20.40 GFLOPS | Progress: (16/20) | 18.50 s
[Task 23/25] Current/Best: 1.55/ 20.40 GFLOPS | Progress: (20/20) | 22.86 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.13/ 7.13 GFLOPS | Progress: (4/20) | 12.87 s
[Task 24/25] Current/Best: 4.29/ 7.13 GFLOPS | Progress: (8/20) | 23.86 s
[Task 24/25] Current/Best: 5.28/ 7.13 GFLOPS | Progress: (12/20) | 26.98 s
[Task 24/25] Current/Best: 2.64/ 9.63 GFLOPS | Progress: (16/20) | 37.96 s
[Task 24/25] Current/Best: 1.78/ 10.31 GFLOPS | Progress: (20/20) | 40.46 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 5.25/ 5.25 GFLOPS | Progress: (4/20) | 13.53 s
[Task 25/25] Current/Best: 3.01/ 9.99 GFLOPS | Progress: (8/20) | 16.09 s
[Task 25/25] Current/Best: 5.65/ 9.99 GFLOPS | Progress: (12/20) | 27.10 s
[Task 25/25] Current/Best: 1.55/ 9.99 GFLOPS | Progress: (16/20) | 37.79 s
[Task 25/25] Current/Best: 5.88/ 9.99 GFLOPS | Progress: (20/20) | 41.12 s
@@ -665,8 +665,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
- class='n02123159 tiger cat' with probability=0.356379
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -723,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 405.51555652999923, 'median': 405.31518149999783, 'std': 0.8260645952274875}
- unoptimized: {'mean': 498.81961337999775, 'median': 498.59456844999386, 'std': 1.129652498706445}
+ optimized: {'mean': 436.79118805999906, 'median': 435.21341339999253, 'std': 4.519102107223159}
+ unoptimized: {'mean': 511.6213232799999, 'median': 510.78641235000646, 'std': 2.559396471416024}
@@ -747,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 33.420 seconds)
+ **Total running time of the script:** ( 12 minutes 31.389 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 253d15ad28..db825a9f21 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
- 1.298e-07 secs/op
+ 1.178e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 7ee0fb4591..66d96fa029 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, 0x2161afa0)), stage(b, placeholder(b, 0x20ca7e00)), 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, 0x20a6dd10)), stage(b, placeholder(b, 0xdf46de0)), 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 136fbc21c4..549f7ca690 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:58.804** total execution time for **tutorial** files:
+**15:56.063** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:33.420 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:31.389 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:23.996 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:15.766 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.508 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.238 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.269 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.405 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.008 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:31.568 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.605 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.661 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.833 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.856 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.164 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.178 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.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 65883ed493..3e7bb06c7f 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,8 +285,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
- naive: 0.000007
+ Numpy running time: 0.000014
+ naive: 0.000014
@@ -392,7 +392,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000007
@@ -447,7 +447,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000024
+ vector: 0.000025
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -504,10 +504,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.8489299997054335e-06 1.0
- naive 6.7816000000000004e-06 0.990169267358795
- parallel 6.0132e-06 0.8779765598799554
- vector 2.3898e-05 3.489304168830435
+ numpy 1.3761110001269116e-05 1.0
+ naive 1.37117e-05 0.9964094465297814
+ parallel 7.024700000000001e-06 0.5104748090344564
+ vector 2.46815e-05 1.7935689779184785
@@ -928,7 +928,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017279
+ Numpy running time: 0.017867
@@ -986,7 +986,7 @@ optimizations.
.. code-block:: none
- none: 3.409947
+ none: 3.196799
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.290654
+ blocking: 0.305880
@@ -1170,7 +1170,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.326935
+ vectorization: 0.338725
# 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: 0.112549
+ loop permutation: 0.113775
# 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: 0.106026
+ array packing: 0.107633
# 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: 0.108030
+ block caching: 0.110563
# 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: 0.143330
+ parallelization: 0.146980
# 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 3.4099473618000005 1.0
- blocking 0.290653928 0.08523707176716454
- vectorization 0.326935117 0.09587688087578618
- loop permutation 0.1125485241 0.03300594178104535
- array packing 0.1060255238 0.03109300893842319
- block caching 0.1080302557 0.031680915931492366
- parallelization 0.1433301978 0.04203296490897755
+ none 3.1967990507 1.0
+ blocking 0.30587973579999994 0.09568312895144965
+ vectorization 0.3387246745 0.10595744966385352
+ loop permutation 0.11377483099999999 0.03559023548104684
+ array packing 0.1076328138 0.033668933233833305
+ block caching 0.1105632885 0.03458562353983121
+ parallelization 0.1469795525 0.045977100896540876
@@ -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 0.508 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 7158fa6560..fadda465af 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-b732e3c02173212abd5067fa1be6ffdc9eb174cb
+a3b51f11b26d721980858091c2df4c7487388c12
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 2c39f766be..29782213e0 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 17.563 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.793 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 2a74d3e12d..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 917ms/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 08fcf07c96..be4035e608 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.zipf9cef832-0fee-4433-88d4-5f1cee5f9164 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.zip14c31332-78a6-4c8f-b504-c8bb0ecb9b7c 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 1ee4857cdc..66c3325e37 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,13 +449,15 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 44.3MB/s]
- 38%|###7 | 15.7M/41.5M [00:00<00:00, 60.0MB/s]
- 53%|#####2 | 22.0M/41.5M [00:00<00:00, 58.3MB/s]
- 67%|######7 | 27.8M/41.5M [00:00<00:00, 36.5MB/s]
- 84%|########3 | 34.7M/41.5M [00:00<00:00, 42.0MB/s]
- 95%|#########4| 39.4M/41.5M [00:00<00:00, 43.2MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 43.2MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 41.8MB/s]
+ 25%|##4 | 10.3M/41.5M [00:00<00:00, 35.6MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 31.5MB/s]
+ 42%|####1 | 17.3M/41.5M [00:00<00:00, 26.5MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.2MB/s]
+ 61%|######1 | 25.4M/41.5M [00:00<00:00, 26.7MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:01<00:00, 31.2MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 36.0MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 30.7MB/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 393a36085e..39a67c0a72 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,13 +432,12 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 14%|#4 | 6.30M/44.7M [00:00<00:01, 36.8MB/s]
- 32%|###2 | 14.3M/44.7M [00:00<00:00, 42.6MB/s]
- 41%|####1 | 18.4M/44.7M [00:00<00:00, 38.7MB/s]
- 54%|#####3 | 24.0M/44.7M [00:00<00:00, 41.3MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 46.1MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 48.8MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 49.0MB/s]
+ 11%|#1 | 5.10M/44.7M [00:00<00:00, 53.5MB/s]
+ 32%|###2 | 14.3M/44.7M [00:00<00:00, 49.1MB/s]
+ 60%|#####9 | 26.7M/44.7M [00:00<00:00, 76.8MB/s]
+ 78%|#######8 | 34.9M/44.7M [00:00<00:00, 70.9MB/s]
+ 97%|#########7| 43.4M/44.7M [00:00<00:00, 76.3MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 72.5MB/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 71635640f0..0446536891 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 21.727 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.761 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 b3d11dc3dc..5039de188a 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,52 +340,52 @@
<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>06:21.320</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:32.485</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
-<col style="width: 11%" />
+<col style="width: 12%" />
<col style="width: 8%" />
</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>01:21.727</p></td>
+<td><p>01:23.761</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>01:17.563</p></td>
+<td><p>01:18.793</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>00:51.258</p></td>
+<td><p>00:53.328</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>00:35.393</p></td>
+<td><p>00:37.162</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:30.493</p></td>
+<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>00:31.318</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:30.422</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:30.940</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>00:27.294</p></td>
+<td><p>00:28.217</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>00:24.376</p></td>
+<td><p>00:25.336</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>00:20.235</p></td>
+<td><p>00:20.1000</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>00:02.559</p></td>
+<td><p>00:02.632</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 3bd8d771b2..9f0a13dce6 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)
- 2648.5399 2647.9239 2652.3422 2646.6950 1.7195
+ 2685.3294 2685.0219 2688.8547 2682.1079 2.1227
</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 042065c891..5591253fcd 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)
- 15.7196 15.5925 16.4317 15.2395 0.4071
+ 16.2886 16.4937 16.5457 15.5124 0.3864
</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 460ee63832..3ebcacbeeb 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,32 +454,30 @@ 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 | 7.99M/170M [00:00<00:04, 36.4MB/s]
- 8%|8 | 14.3M/170M [00:00<00:03, 42.4MB/s]
- 11%|# | 18.5M/170M [00:00<00:04, 38.1MB/s]
- 15%|#5 | 25.6M/170M [00:00<00:03, 48.5MB/s]
- 18%|#7 | 30.6M/170M [00:00<00:03, 47.0MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 48.0MB/s]
- 26%|##6 | 44.7M/170M [00:01<00:02, 46.4MB/s]
- 29%|##9 | 50.1M/170M [00:01<00:02, 45.7MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 45.6MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:02, 46.7MB/s]
- 40%|#### | 68.5M/170M [00:01<00:02, 43.9MB/s]
- 46%|####6 | 78.3M/170M [00:01<00:01, 57.8MB/s]
- 51%|##### | 86.3M/170M [00:01<00:01, 61.3MB/s]
- 54%|#####4 | 92.4M/170M [00:01<00:01, 55.4MB/s]
- 58%|#####7 | 98.0M/170M [00:02<00:01, 49.3MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 47.4MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 48.7MB/s]
- 72%|#######2 | 123M/170M [00:02<00:00, 63.6MB/s]
- 76%|#######6 | 130M/170M [00:02<00:00, 63.9MB/s]
- 80%|######## | 136M/170M [00:02<00:00, 53.1MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 57.6MB/s]
- 88%|########8 | 150M/170M [00:03<00:00, 42.1MB/s]
- 93%|#########3| 158M/170M [00:03<00:00, 47.5MB/s]
- 96%|#########6| 164M/170M [00:03<00:00, 44.4MB/s]
- 99%|#########9| 168M/170M [00:03<00:00, 44.2MB/s]
-100%|##########| 170M/170M [00:03<00:00, 49.1MB/s]
+ 1%|1 | 2.05M/170M [00:00<00:12, 14.0MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:04, 34.5MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:03, 43.7MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:03, 48.6MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:02, 55.8MB/s]
+ 26%|##6 | 44.9M/170M [00:00<00:01, 77.6MB/s]
+ 31%|###1 | 52.8M/170M [00:00<00:01, 71.9MB/s]
+ 35%|###5 | 60.1M/170M [00:01<00:01, 68.4MB/s]
+ 39%|###9 | 66.9M/170M [00:01<00:01, 61.0MB/s]
+ 45%|####4 | 76.0M/170M [00:01<00:01, 69.4MB/s]
+ 50%|####9 | 84.7M/170M [00:01<00:01, 75.2MB/s]
+ 54%|#####4 | 92.2M/170M [00:01<00:01, 67.6MB/s]
+ 58%|#####8 | 99.0M/170M [00:01<00:01, 44.3MB/s]
+ 61%|######1 | 104M/170M [00:02<00:01, 43.6MB/s]
+ 69%|######8 | 117M/170M [00:02<00:00, 61.6MB/s]
+ 73%|#######3 | 124M/170M [00:02<00:00, 49.6MB/s]
+ 77%|#######6 | 130M/170M [00:02<00:01, 40.3MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 42.3MB/s]
+ 83%|########3 | 141M/170M [00:02<00:00, 40.8MB/s]
+ 86%|########5 | 146M/170M [00:02<00:00, 40.7MB/s]
+ 89%|########9 | 152M/170M [00:03<00:00, 46.2MB/s]
+ 94%|#########3| 159M/170M [00:03<00:00, 52.5MB/s]
+ 99%|#########8| 168M/170M [00:03<00:00, 60.5MB/s]
+100%|##########| 170M/170M [00:03<00:00, 53.9MB/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=& [...]
@@ -577,7 +575,7 @@ 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 22.469 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 28.341 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 90de2edd7a..8daeaedc2e 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,9 +495,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 47%|####6 | 6.30M/13.6M [00:00<00:00, 45.4MB/s]
- 79%|#######8 | 10.6M/13.6M [00:00<00:00, 35.6MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 39.3MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 35.7MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 43.8MB/s]
</pre></div>
</div>
</div>
@@ -588,7 +587,7 @@ 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)
- 88.8823 88.8114 91.4137 88.5533 0.3346
+ 90.3648 90.2665 94.9289 90.1163 0.5225
</pre></div>
</div>
<div class="admonition note">
@@ -627,7 +626,7 @@ 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 12.248 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.271 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 c25a9fa806..d20671d874 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)
- 114.8005 114.6520 118.6461 113.4900 0.9052
+ 121.1218 120.9935 125.8877 120.4494 0.6141
</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 32.735 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 36.342 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 8c1be5de4f..c498ea9ca0 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 45.123 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.188 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 45f3337bf4..904d39a051 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]
- 4%|3 | 5306/132723 [00:00<00:02, 53048.04KB/s]
- 10%|9 | 12961/132723 [00:00<00:01, 66866.60KB/s]
- 15%|#4 | 19648/132723 [00:00<00:01, 64055.05KB/s]
- 21%|## | 27417/132723 [00:00<00:01, 69284.62KB/s]
- 26%|##5 | 34368/132723 [00:00<00:02, 48212.22KB/s]
- 32%|###1 | 42202/132723 [00:00<00:01, 56055.74KB/s]
- 38%|###7 | 50058/132723 [00:00<00:01, 62154.56KB/s]
- 44%|####3 | 57997/132723 [00:00<00:01, 66965.21KB/s]
- 50%|####9 | 65870/132723 [00:01<00:00, 70317.40KB/s]
- 55%|#####5 | 73636/132723 [00:01<00:00, 72438.14KB/s]
- 61%|######1 | 81402/132723 [00:01<00:00, 73962.69KB/s]
- 67%|######7 | 89186/132723 [00:01<00:00, 75102.87KB/s]
- 73%|#######3 | 96999/132723 [00:01<00:00, 75997.57KB/s]
- 79%|#######8 | 104753/132723 [00:01<00:00, 76452.52KB/s]
- 85%|########4 | 112537/132723 [00:01<00:00, 76843.32KB/s]
- 91%|######### | 120355/132723 [00:01<00:00, 77240.05KB/s]
- 97%|#########6| 128214/132723 [00:01<00:00, 77641.98KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 70218.84KB/s]
+ 3%|3 | 4096/132723 [00:00<00:03, 40956.13KB/s]
+ 10%|9 | 12773/132723 [00:00<00:01, 67894.94KB/s]
+ 16%|#6 | 21495/132723 [00:00<00:01, 76714.42KB/s]
+ 23%|##2 | 30099/132723 [00:00<00:01, 80393.11KB/s]
+ 29%|##9 | 38706/132723 [00:00<00:01, 82435.85KB/s]
+ 36%|###5 | 47450/132723 [00:00<00:01, 84127.53KB/s]
+ 42%|####2 | 56109/132723 [00:00<00:00, 84929.91KB/s]
+ 49%|####8 | 64874/132723 [00:00<00:00, 85785.43KB/s]
+ 55%|#####5 | 73542/132723 [00:00<00:00, 86062.18KB/s]
+ 62%|######1 | 82200/132723 [00:01<00:00, 86218.43KB/s]
+ 68%|######8 | 90822/132723 [00:01<00:00, 86130.02KB/s]
+ 75%|#######4 | 99436/132723 [00:01<00:00, 85168.29KB/s]
+ 81%|########1 | 107956/132723 [00:01<00:00, 83901.06KB/s]
+ 88%|########7 | 116663/132723 [00:01<00:00, 84839.67KB/s]
+ 94%|#########4| 125303/132723 [00:01<00:00, 85303.41KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83144.71KB/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 37.296 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 45.869 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 f91478f83f..6bcea9ab42 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>14:57.771</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>15:20.582</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>03:37.296</p></td>
+<td><p>03:45.869</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>03:22.469</p></td>
+<td><p>03:28.341</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>02:32.735</p></td>
+<td><p>02:36.342</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:45.123</p></td>
+<td><p>01:42.188</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>01:12.248</p></td>
+<td><p>01:16.271</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>00:54.374</p></td>
+<td><p>00:55.380</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>00:39.490</p></td>
+<td><p>00:41.012</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>00:27.205</p></td>
+<td><p>00:27.783</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>00:26.826</p></td>
+<td><p>00:27.390</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 b2b479294c..737f2b089f 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.zip4b0bf4fe-1e39-4a22-a4f7-5acdb7ca7803 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.zip4ef994b4-0c9d-4505-a33d-d1b12a530929 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 faf6c0c2b8..ed1d939d4b 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>00:51.465</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:54.229</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>00:47.822</p></td>
+<td><p>00:50.364</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>00:02.609</p></td>
+<td><p>00:02.758</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>00:01.026</p></td>
+<td><p>00:01.098</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 6dff287a40..f03737e7ad 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: 22476us [22476us] (49.41%; 49.41%)
-FoldScaleAxis: 23015us [7us] (50.59%; 50.59%)
- FoldConstant: 23008us [1684us] (50.58%; 99.97%)
- InferType: 21324us [21324us] (46.87%; 92.68%)
+InferType: 22349us [22349us] (48.77%; 48.77%)
+FoldScaleAxis: 23473us [9us] (51.23%; 51.23%)
+ FoldConstant: 23463us [1745us] (51.21%; 99.96%)
+ InferType: 21718us [21718us] (47.40%; 92.56%)
</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: 21143us [21143us] (48.25%; 48.25%)
-FoldScaleAxis: 22673us [5us] (51.75%; 51.75%)
- FoldConstant: 22668us [1603us] (51.73%; 99.98%)
- InferType: 21065us [21065us] (48.08%; 92.93%)
+InferType: 21888us [21888us] (48.39%; 48.39%)
+FoldScaleAxis: 23342us [6us] (51.61%; 51.61%)
+ FoldConstant: 23336us [1727us] (51.59%; 99.97%)
+ InferType: 21609us [21609us] (47.78%; 92.60%)
</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 d660c66615..565b0afb85 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: 54.150718 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 47.488960 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 7fd888d8e5..5f1560cdfe 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: 9.267065 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.354188 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 dd94b8aa8d..cb34b2fb5e 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: 0.017562
-Baseline: 3.256667
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018650
+Baseline: 3.225731
</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: 0.297628
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.312922
</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: 0.330059
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.340193
</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: 0.111028
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.122795
</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: 0.107514
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109806
</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: 0.110178
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112097
</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: 0.143505
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147239
</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 3b25304f35..d5963cad82 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.076</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.748</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.361</p></td>
+<td><p>00:32.062</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>00:01.610</p></td>
+<td><p>00:01.629</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>00:01.104</p></td>
+<td><p>00:01.058</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 697fe471c8..e524789a73 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>09:37.615</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:08.840</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>05:57.833</p></td>
+<td><p>06:20.417</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>01:37.847</p></td>
+<td><p>01:41.535</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>01:05.698</p></td>
+<td><p>01:08.426</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>00:30.164</p></td>
+<td><p>00:31.109</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>00:13.281</p></td>
+<td><p>00:14.016</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>00:12.793</p></td>
+<td><p>00:13.336</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 0703abb503..37c3e0e43f 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
@@ -506,13 +506,13 @@ 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, 28)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([72], "float32", "shared")
+ T.launch_thread(blockIdx_x, 32)
+ conv2d_nchw = T.allocate([16], "float32", "local")
+ pad_temp_shared = T.allocate([4032], "float32", "shared")
kernel_shared = T.allocate([3072], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 64)
- conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
+ T.launch_thread(threadIdx_x, 49)
+ conv2d_nchw_1 = T.Buffer((16,), data=conv2d_nchw, scope="local")
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
@@ -527,460 +527,509 @@ class Module:
conv2d_nchw_1[11] = T.float32(0)
conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(64, 3):
- cse_var_2: T.int32 = rc_outer_outer * 72
- cse_var_1: T.int32 = ry_outer_outer * 3
+ conv2d_nchw_1[14] = T.float32(0)
+ conv2d_nchw_1[15] = T.float32(0)
+ for rc_outer_outer, rx_outer_outer in T.grid(8, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 3136
+ cse_var_1: T.int32 = rc_outer_outer * 576
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((72,), data=pad_temp_shared, scope="shared")
- with T.launch_thread(threadIdx_x_1, 64):
- data_1 = T.Buffer((25088,), data=data.data)
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 * 4 % 9 and threadIdx_x_1 * 4 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 * 4 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 * 4 % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 1) % 9 and (threadIdx_x_1 * 4 + 1) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 1) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 1) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 2] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 2) % 9 and (threadIdx_x_1 * 4 + 2) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 2) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 2) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 3] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 3) % 9 and (threadIdx_x_1 * 4 + 3) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 3) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1 = T.Buffer((4032,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 49) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 147) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 245] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 245) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 343] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 343) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 441] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 335], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 539] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 539) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 637] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 637) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 735] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 735) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 833] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 833) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 678], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 931] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 931) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1029] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1029) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1127] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1127) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1225] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1225) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1323] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 1021], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1421] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1421) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1519] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1519) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1617] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1617) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1715] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1715) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 1364], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1813] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1813) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1911] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1911) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2009] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2009) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2058] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2058) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2107] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2107) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2156] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2156) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2205] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 1707], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2254] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2254) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2303] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2303) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2352] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2352) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2401] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2401) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2450] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2450) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2499] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2499) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2548] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2548) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2597] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2597) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2646] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 2050], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2695] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2695) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2744] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2744) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2793] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2793) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2842] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2842) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2891] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2891) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2940] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2940) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 2989] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 2989) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3038] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3038) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3087] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 2393], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3136] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3136) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3185] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3185) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3234] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3234) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3283] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3283) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3332] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3332) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3381] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3381) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3430] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3430) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3479] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3479) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3528] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 2736], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3577] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3577) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3626] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3626) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3675] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3675) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3724] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3724) // 63 * 49 + threadIdx_x_1 + rx_outer_outer - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3773] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 8) % 9 and (threadIdx_x_1 // 7 + 8) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3773) // 63 * 49 + (threadIdx_x_1 // 7 + 8) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3822] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 6) % 9 and (threadIdx_x_1 // 7 + 6) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3822) // 63 * 49 + (threadIdx_x_1 // 7 + 6) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3871] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 4) % 9 and (threadIdx_x_1 // 7 + 4) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3871) // 63 * 49 + (threadIdx_x_1 // 7 + 4) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3920] = T.if_then_else(threadIdx_x_1 < 42 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 3920) // 63 * 49 + threadIdx_x_1 + rx_outer_outer + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 3969] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 + rx_outer_outer + 3079], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ if T.likely(threadIdx_x_1 < 14):
+ pad_temp_shared_1[threadIdx_x_1 + 4018] = T.if_then_else(threadIdx_x_1 < 7 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 4018) // 63 * 49 + rx_outer_outer + threadIdx_x_1 + 41], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
kernel_shared_1 = T.Buffer((3072,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 64) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 128) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 192] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 256) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 320) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 384] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 448) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 512) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 576] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 640) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 704) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 768] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 832) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 896) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 960] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1024) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1088) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1152] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1216) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1280) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1408) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1472) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1536] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 294912]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1600) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1664) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1728] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 331776]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1792) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1856) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1920] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 368640]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 1984) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2048) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2112] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 405504]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2176) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2240) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2304] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 442368]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2368) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2432) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2496] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 479232]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2560) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2624) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 516096]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2752) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2816) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2880] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 552960]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 2944) // 24 * 24 + (threadIdx_x_2 + 16) % 24 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[(threadIdx_x_2 + 3008) // 24 * 24 + (threadIdx_x_2 + 8) % 24 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 47]
- for i1_inner, i3_inner in T.grid(2, 7):
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 49] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 147]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 294]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 147] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 147) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 147) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 12]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 245] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 245) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 159]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 306]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 343] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 343) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 151) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 392] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 24]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 441] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 441) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 171]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 490] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 318]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 539] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 539) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 155) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 588] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 588) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 36]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 637] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 637) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 183]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 686] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 686) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 330]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 735] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 735) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 159) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 48]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 833] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 833) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 195]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 882] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 882) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 342]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 931] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 931) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 163) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 980] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 980) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 60]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1029] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1029) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 207]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1078] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1078) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 354]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1127] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1127) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 167) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1176] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1176) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 72]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1225] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1225) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 219]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1274] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1274) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 366]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1323] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1323) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 171) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1372] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1372) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 84]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1421] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1421) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 231]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1470] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1470) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 378]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1519] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1519) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 175) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1568) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 96]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1617] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1617) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 243]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1666] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1666) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 390]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1715] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1715) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 179) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1764] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1764) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 108]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1813] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1813) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 255]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1862] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1862) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 402]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1911] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1911) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 183) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1960] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1960) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 120]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2009] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2009) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 267]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2058] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2058) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 414]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2107] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2107) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 187) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2156] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2156) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 132]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2205] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2205) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 279]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2254] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2254) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 426]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2303] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2303) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 191) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2352] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2352) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2401] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2401) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 291]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2450] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2450) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 146) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2499] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2499) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 9]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2548] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2548) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 156]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2597] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2597) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 303]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2646] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2646) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 150) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2695] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2695) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 21]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2744] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2744) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 168]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2793] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2793) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 315]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2842] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2842) // 192 * 4608 + cse_var_1 + (threadIdx_x_2 + 154) % 192 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2891] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2891) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 33]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2940] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2940) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 180]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2989] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2989) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 327]
+ with T.launch_thread(threadIdx_x_2, 49):
+ if T.likely(threadIdx_x_2 < 34):
+ kernel_shared_1[threadIdx_x_2 + 3038] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 3038) // 192 * 4608 + cse_var_1 + threadIdx_x_2 * 3 + rx_outer_outer + 474]
+ for rc_outer_inner in range(16):
+ cse_var_3: T.int32 = rc_outer_inner * 12
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 192]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 384]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 576]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 768]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 960]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1152]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1344]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1536]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1728]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 1920]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2112]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2304]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2496]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2688]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x] * kernel_shared_1[cse_var_3 + 2880]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 193]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 385]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 577]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 769]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 961]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1153]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1345]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1537]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1729]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 1921]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2113]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2305]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2497]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2689]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 7] * kernel_shared_1[cse_var_3 + 2881]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 194]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 386]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 578]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 770]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 962]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1154]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1346]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1538]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1730]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 1922]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2114]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2306]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2498]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2690]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 14] * kernel_shared_1[cse_var_3 + 2882]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 195]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 387]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 579]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 771]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 963]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1155]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1347]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1539]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1731]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 1923]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2115]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2307]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2499]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2691]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 63] * kernel_shared_1[cse_var_3 + 2883]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 196]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 388]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 580]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 772]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 964]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1156]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1348]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1540]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1732]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 1924]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2116]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2308]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2500]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2692]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 70] * kernel_shared_1[cse_var_3 + 2884]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 197]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 389]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 581]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 773]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 965]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1157]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1349]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1541]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1733]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 1925]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2117]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2309]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2501]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2693]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 77] * kernel_shared_1[cse_var_3 + 2885]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 198]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 390]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 582]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 774]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 966]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1158]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1350]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1542]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1734]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 1926]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2118]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2310]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2502]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2694]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 126] * kernel_shared_1[cse_var_3 + 2886]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 199]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 391]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 583]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 775]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 967]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1159]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1351]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1543]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1735]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 1927]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2119]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2311]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2503]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2695]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 133] * kernel_shared_1[cse_var_3 + 2887]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 200]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 392]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 584]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 776]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 968]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1160]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1352]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1544]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1736]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 1928]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2120]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2312]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2504]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2696]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 140] * kernel_shared_1[cse_var_3 + 2888]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 201]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 393]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 585]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 777]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 969]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1161]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1353]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1545]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1737]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 1929]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2121]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2313]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2505]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2697]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 189] * kernel_shared_1[cse_var_3 + 2889]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 202]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 394]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 586]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 778]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 970]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1162]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1354]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1546]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1738]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 1930]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2122]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2314]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2506]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2698]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 196] * kernel_shared_1[cse_var_3 + 2890]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 203]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 395]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 587]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 779]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 971]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1163]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1355]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1547]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1739]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 1931]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2123]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2315]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2507]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2699]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 252 + threadIdx_x + 203] * kernel_shared_1[cse_var_3 + 2891]
+ for i1_inner in range(16):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x // 7 * 6272 + threadIdx_x * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -1014,7 +1063,7 @@ 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: 0.361 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.363 ms
</pre></div>
</div>
</div>
@@ -1043,36 +1092,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=16)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_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=64)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1092,12 +1141,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=4)
+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=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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, "unroll_explicit", True)
@@ -1117,9 +1166,9 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
+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[16];
+ __shared__ float pad_temp_shared[4032];
__shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -1135,412 +1184,360 @@ extern "C" __global__ void __launch_bounds__(64) default_function_kern
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1707)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2050)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 3079)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 14) {
+ pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((int)threadIdx.x) < 7) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 63) * 49)) + rx_outer_outer) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 147)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 294)];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 147) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 147) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 245) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 159)];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 306)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 343) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 151) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 441) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 171)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 318)];
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 539) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 155) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 637) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 183)];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 330)];
+ kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 735) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 159) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 833)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 833) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 195)];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 342)];
+ kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 931) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 163) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 60)];
+ kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1029) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 207)];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 354)];
+ kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1127) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 167) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1225)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1225) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 219)];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 366)];
+ kernel_shared[(((int)threadIdx.x) + 1323)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1323) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 171) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 84)];
+ kernel_shared[(((int)threadIdx.x) + 1421)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1421) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 231)];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 378)];
+ kernel_shared[(((int)threadIdx.x) + 1519)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1519) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 175) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1617)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1617) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 243)];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 390)];
+ kernel_shared[(((int)threadIdx.x) + 1715)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1715) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 179) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 108)];
+ kernel_shared[(((int)threadIdx.x) + 1813)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1813) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 255)];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 402)];
+ kernel_shared[(((int)threadIdx.x) + 1911)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1911) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 183) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 120)];
+ kernel_shared[(((int)threadIdx.x) + 2009)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2009) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 267)];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 414)];
+ kernel_shared[(((int)threadIdx.x) + 2107)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2107) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 187) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 132)];
+ kernel_shared[(((int)threadIdx.x) + 2205)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2205) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 279)];
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 426)];
+ kernel_shared[(((int)threadIdx.x) + 2303)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2303) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 191) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 2401)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2401) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 291)];
+ kernel_shared[(((int)threadIdx.x) + 2450)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2450) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 146) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2499)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2499) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 9)];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 156)];
+ kernel_shared[(((int)threadIdx.x) + 2597)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2597) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 303)];
+ kernel_shared[(((int)threadIdx.x) + 2646)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2646) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 150) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2695)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2695) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 21)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 168)];
+ kernel_shared[(((int)threadIdx.x) + 2793)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2793) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 315)];
+ kernel_shared[(((int)threadIdx.x) + 2842)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2842) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 154) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2891)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2891) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 33)];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 180)];
+ kernel_shared[(((int)threadIdx.x) + 2989)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2989) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 327)];
+ if (((int)threadIdx.x) < 34) {
+ kernel_shared[(((int)threadIdx.x) + 3038)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3038) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 474)];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 64) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 128) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((((((int)threadIdx.x) + 256) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 320) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((((((int)threadIdx.x) + 448) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 512) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((((((int)threadIdx.x) + 640) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 704) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((((((int)threadIdx.x) + 832) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 896) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((((((int)threadIdx.x) + 1024) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1088) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((((((int)threadIdx.x) + 1216) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1280) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((((((int)threadIdx.x) + 1408) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1472) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((((((int)threadIdx.x) + 1600) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1664) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((((((int)threadIdx.x) + 1792) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 1856) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((((((int)threadIdx.x) + 1984) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2048) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((((((int)threadIdx.x) + 2176) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2240) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((((((int)threadIdx.x) + 2368) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2432) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((((((int)threadIdx.x) + 2560) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2624) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((((((int)threadIdx.x) + 2752) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 2816) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((((((int)threadIdx.x) + 2944) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 3008) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 192)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 384)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 768)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 960)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1152)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1344)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1536)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1728)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 1920)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2112)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2304)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2496)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2688)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rc_outer_inner * 252) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 12) + 2880)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 193)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 385)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 577)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 769)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 961)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1153)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1345)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1537)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1729)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 1921)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2113)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2305)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2497)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2689)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 12) + 2881)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 194)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 386)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 770)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 962)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1154)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1346)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1538)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1730)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 1922)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2114)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2306)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2498)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2690)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 12) + 2882)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 195)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 387)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 579)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 771)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 963)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1155)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1347)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1539)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1731)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 1923)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2115)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2307)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2499)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2691)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 12) + 2883)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 196)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 388)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 580)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 772)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 964)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1156)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1348)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1540)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1732)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 1924)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2116)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2308)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2500)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2692)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 12) + 2884)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 197)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 389)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 773)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 965)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1157)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1349)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1541)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1733)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 1925)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2117)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2309)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2501)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2693)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 12) + 2885)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 198)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 390)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 582)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 774)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 966)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1158)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1350)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1542)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1734)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 1926)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2118)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2310)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2502)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2694)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 12) + 2886)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 199)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 391)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 583)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 775)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 967)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1159)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1351)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1543)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1735)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 1927)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2119)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2311)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2503)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2695)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 12) + 2887)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 200)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 392)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 776)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 968)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1160)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1352)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1544)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1736)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 1928)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2120)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2312)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2504)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2696)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 12) + 2888)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 201)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 393)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 777)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 969)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1161)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1353)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1545)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1737)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 1929)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2121)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2313)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2505)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2697)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 12) + 2889)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 202)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 394)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 586)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 778)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 970)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1162)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1354)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1546)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1738)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 1930)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2122)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2314)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2506)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2698)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 12) + 2890)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 203)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 395)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 779)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 971)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1163)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1355)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1547)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1739)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 1931)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2123)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2315)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2507)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2699)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 252) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 12) + 2891)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1575,7 +1572,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 57.833 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 20.417 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 f7cdff320b..6099bc241c 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)
- 7.9264 7.9225 7.9352 7.9216 0.0062
+ 7.9084 7.9097 7.9131 7.9023 0.0045
</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 5.698 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.426 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 b34d969367..d1ebb1f7b8 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)
- 737.3005 734.2678 743.7643 733.8693 4.5735
+ 749.1448 748.3357 750.9397 748.1590 1.2712
</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 37.847 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.535 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 ba5ad429c8..031eaea7ec 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,86 +632,27 @@ 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 in T.parallel(2):
- compute_1 = T.allocate([1024], "float32", "global")
- for i1_outer in range(32):
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_inner_init in range(64):
- cse_var_1: T.int32 = i_inner_init * 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(placeholder_5[i1_outer + 1] - placeholder_5[i1_outer], 64):
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- 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)
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_2: T.int32 = i_inner * 16
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_3: T.int32 = i_inner * 16 + 1
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 1] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_4: T.int32 = i_inner * 16 + 2
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 2] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_5: T.int32 = i_inner * 16 + 3
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 3] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_6: T.int32 = i_inner * 16 + 4
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 4] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_7: T.int32 = i_inner * 16 + 5
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 5] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_8: T.int32 = i_inner * 16 + 6
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 6] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_9: T.int32 = i_inner * 16 + 7
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 7] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_10: T.int32 = i_inner * 16 + 8
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 8] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_11: T.int32 = i_inner * 16 + 9
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 9] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_12: T.int32 = i_inner * 16 + 10
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 10] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_13: T.int32 = i_inner * 16 + 11
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 11] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_14: T.int32 = i_inner * 16 + 12
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 12] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_15: T.int32 = i_inner * 16 + 13
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 13] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_16: T.int32 = i_inner * 16 + 14
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 14] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[i1_outer + 1] - placeholder_5[i1_outer]):
- cse_var_17: T.int32 = i_inner * 16 + 15
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[i1_outer] * 16 + elem_idx * 16 + 15] * T.max(placeholder_7[i0_outer * 16384 + i_inner * 256 + placeholder_8[placeholder_5[i1_outer] + elem_idx]], T.float32(0))
- for i0_inner in range(64):
- cse_var_18: T.int32 = i0_outer * 32768 + i0_inner * 512 + i1_outer * 16
+ for i0_outer in T.parallel(32):
+ compute_1 = T.allocate([128], "float32", "global")
+ for i1_outer in range(16):
+ compute_2 = T.Buffer((128,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init, j_init in T.grid(4, 16):
+ compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i1_outer * 2 + nb_j_inner, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 4, 16):
+ cse_var_1 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_3: T.int32 = i1_outer * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(4):
+ cse_var_4: T.int32 = i0_outer * 2048 + i0_inner * 512 + i1_outer * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_18:cse_var_18 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_18:cse_var_18 + 16], T.Broadcast(T.float32(0), 16))
+ compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
</pre></div>
</div>
</div>
@@ -745,7 +686,7 @@ 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: 1.800 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.276 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 f1cfd99ee1..5038212de2 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>00:32.924</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:52.317</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:32.891</p></td>
+<td><p>00:52.284</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 70fda378a1..951e8b4a23 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -690,7 +690,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9672678
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4128886
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)
@@ -813,7 +813,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7612234
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7535911
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)
@@ -936,7 +936,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2799178
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9580633
No: 4 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)
@@ -1059,9 +1059,26 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6669761
-No: 5 GFLOPS: 6.64/6.64 result: MeasureResult(costs=(0.034884544249999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9321067333221436, timestamp=1677105940.151384) [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2527987
-No: 6 GFLOPS: 0.00/6.64 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2439798
+No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8618611
+No: 6 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
@@ -1183,9 +1200,9 @@ 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, 4, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9414201
-No: 7 GFLOPS: 39.31/39.31 result: MeasureResult(costs=(0.005888479703703704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.340256690979004, timestamp=1677105941.1244223) [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7201636
-No: 8 GFLOPS: 0.00/39.31 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, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10124156
+No: 7 GFLOPS: 35.64/35.64 result: MeasureResult(costs=(0.0064950799375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4253714084625244, timestamp=1677113892.7945414) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6432503
+No: 8 GFLOPS: 0.00/35.64 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
@@ -1307,8 +1324,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8079014
-No: 9 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6696159
+No: 9 GFLOPS: 0.00/35.64 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
@@ -1430,8 +1447,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1639059
-No: 10 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,528487
+No: 10 GFLOPS: 0.00/35.64 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
@@ -1553,9 +1570,8 @@ 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, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9381190
-No: 11 GFLOPS: 1.76/39.31 result: MeasureResult(costs=(0.1316362915,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9758658409118652, timestamp=1677105944.317569) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,400679
-No: 12 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5261283
+No: 11 GFLOPS: 0.00/35.64 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
@@ -1677,8 +1693,8 @@ 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, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7865712
-No: 13 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5067425
+No: 12 GFLOPS: 0.00/35.64 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
@@ -1800,9 +1816,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4602651
-No: 14 GFLOPS: 9.04/39.31 result: MeasureResult(costs=(0.025608671,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1361608505249023, timestamp=1677105947.650252) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8987724
-No: 15 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9030182
+No: 13 GFLOPS: 0.00/35.64 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
@@ -1924,8 +1939,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1150657
-No: 16 GFLOPS: 0.00/39.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8964907
+No: 14 GFLOPS: 12.02/35.64 result: MeasureResult(costs=(0.01925196833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5436971187591553, timestamp=1677113901.3400843) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7758445
+No: 15 GFLOPS: 12.20/35.64 result: MeasureResult(costs=(0.0189794985,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.47144341468811, timestamp=1677113902.2060459) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4727289
+No: 16 GFLOPS: 0.00/35.64 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
@@ -2047,10 +2064,8 @@ 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5993857
-No: 17 GFLOPS: 50.74/50.74 result: MeasureResult(costs=(0.004562757636363637,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.40277099609375, timestamp=1677105949.255102) [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6781107
-No: 18 GFLOPS: 204.72/204.72 result: MeasureResult(costs=(0.0011308382808988763,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0636248588562012, timestamp=1677105949.9692926) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 7, 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', 0), ('unroll_explicit', 1)],None,5824450
-No: 19 GFLOPS: 0.00/204.72 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9714392
+No: 17 GFLOPS: 0.00/35.64 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
@@ -2172,130 +2187,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7802662
-No: 20 GFLOPS: 0.00/204.72 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- 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:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- 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:1734
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:451
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1753
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1697
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7308566
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6582345
+No: 18 GFLOPS: 55.02/55.02 result: MeasureResult(costs=(0.0042074783,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.742863416671753, timestamp=1677113907.1546783) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10105368
+No: 19 GFLOPS: 16.00/55.02 result: MeasureResult(costs=(0.014471026714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.590982437133789, timestamp=1677113907.9367762) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3098800
+No: 20 GFLOPS: 50.97/55.02 result: MeasureResult(costs=(0.004541591782608695,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9592344760894775, timestamp=1677113908.6984577) [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6852641
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2334,9 +2229,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 7, 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', 0), ('unroll_explicit', 1)],None,5824450
+[('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10105368
Finish loading 20 records
-Time cost of this operator: 0.001482
+Time cost of this operator: 0.004236
</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_aot.html b/docs/how_to/work_with_microtvm/micro_aot.html
index 0c532dbafa..015722cec6 100644
--- a/docs/how_to/work_with_microtvm/micro_aot.html
+++ b/docs/how_to/work_with_microtvm/micro_aot.html
@@ -469,8 +469,8 @@ This model is originally from <a class="reference external" href="https://github
To test this model, we use samples from <a class="reference external" href="https://ai.googleblog.com/2017/08/launching-speech-commands-dataset.html">KWS dataset provided by Google</a>.</p>
<p><strong>Note:</strong> By default this tutorial runs on x86 CPU using CRT, if you would like to run on Zephyr platform
you need to export <cite>TVM_MICRO_USE_HW</cite> environment variable.</p>
-<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">MODEL_URL</span></a> <span class="o">=</span> <span class="s2">"https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/model/keyword_spotting_quant.tflite"</span>
-<a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">MODEL_PATH</span></a> <span class="o">=</span> <span class="n">download_testdata</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><sp [...]
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">MODEL_URL</span></a> <span class="o">=</span> <span class="s2">"https://github.com/mlcommons/tiny/raw/bceb91c5ad2e2deb295547d81505721d3a87d578/benchmark/training/keyword_spotting/trained_models/kws_ref_mode [...]
+<a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">MODEL_PATH</span></a> <span class="o">=</span> <span class="n">download_testdata</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><sp [...]
<a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">SAMPLE_URL</span></a> <span class="o">=</span> <span class="s2">"https://github.com/tlc-pack/web-data/raw/main/testdata/microTVM/data/keyword_spotting_int8_6.pyc.npy"</span>
<a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">SAMPLE_PATH</span></a> <span class="o">=</span> <span class="n">download_testdata</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><s [...]
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 28265bb1ff..bc297d4aca 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 309.9 98.743 (1, 2, 10, 10, 3) 2 1 [309.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.951 0.94 (1, 6, 10, 10) 1 1 [2.951]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.994 0.317 (1, 1, 10, 10, 3) 1 1 [0.994]
-Total_time - 313.844 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.0 98.751 (1, 2, 10, 10, 3) 2 1 [317.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.04 0.947 (1, 6, 10, 10) 1 1 [3.04]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.302 (1, 1, 10, 10, 3) 1 1 [0.969]
+Total_time - 321.009 - - - - -
</pre></div>
</div>
</div>
@@ -698,13 +698,13 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 133.6 98.071 (1, 6, 10, 10, 1) 2 1 [133.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.705 1.251 (1, 6, 10, 10) 1 1 [1.705]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.677 (1, 1, 10, 10, 3) 1 1 [0.923]
-Total_time - 136.227 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 137.5 98.056 (1, 6, 10, 10, 1) 2 1 [137.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.762 1.256 (1, 6, 10, 10) 1 1 [1.762]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.687 (1, 1, 10, 10, 3) 1 1 [0.964]
+Total_time - 140.226 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.136 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.095 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 143c518e1c..4cdfdb7bca 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -454,7 +454,8 @@ 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, 144MB/s]
+ 61%|###### | 2.09M/3.42M [00:00<00:00, 10.9MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 17.2MB/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 +581,7 @@ 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 10.276 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.077 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 1b675aa559..d91068ff3b 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/tmpbo72an5e/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp8i34xudc/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], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpbo72an5e/images/target contains 8144 images
-/tmp/tmpbo72an5e/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], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp8i34xudc/images/target contains 8144 images
+/tmp/tmp8i34xudc/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 - 46s - loss: 0.2246 - accuracy: 0.9230 - val_loss: 0.1153 - val_accuracy: 0.9622 - 46s/epoch - 141ms/step
+328/328 - 47s - loss: 0.2288 - accuracy: 0.9205 - val_loss: 0.1645 - val_accuracy: 0.9418 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 42s - loss: 0.1061 - accuracy: 0.9602 - val_loss: 0.1102 - val_accuracy: 0.9630 - 42s/epoch - 129ms/step
+328/328 - 43s - loss: 0.1080 - accuracy: 0.9593 - val_loss: 0.0963 - val_accuracy: 0.9626 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 42s - loss: 0.0671 - accuracy: 0.9744 - val_loss: 0.1180 - val_accuracy: 0.9619 - 42s/epoch - 128ms/step
+328/328 - 43s - loss: 0.0722 - accuracy: 0.9723 - val_loss: 0.0731 - val_accuracy: 0.9739 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7f5f5a539450>
+<keras.callbacks.History object at 0x7fcf124f9950>
</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 38.407 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 52.569 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 3e761ebc33..e217e73c25 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>07:16.827</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:38.436</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>04:38.407</p></td>
+<td><p>04:52.569</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:12.136</p></td>
+<td><p>01:15.095</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:10.276</p></td>
+<td><p>01:14.077</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>00:09.226</p></td>
+<td><p>00:09.697</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>00:06.782</p></td>
+<td><p>00:06.998</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 db43206bc4..e770f445ae 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>00:45.166</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:46.051</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>00:33.061</p></td>
+<td><p>00:33.845</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>00:10.456</p></td>
+<td><p>00:10.379</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>00:01.643</p></td>
+<td><p>00:01.821</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 d209745a6f..2322de7ff1 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 0x7f5e07b20320>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fcdbddff320>
</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 55d16da498..5bef35528d 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.500</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.217</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.947</p></td>
+<td><p>00:05.509</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>00:01.183</p></td>
+<td><p>00:01.284</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.584</p></td>
+<td><p>00:00.621</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>00:00.564</p></td>
+<td><p>00:00.573</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>00:00.113</p></td>
+<td><p>00:00.118</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.052</p></td>
+<td><p>00:00.053</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>
@@ -377,7 +377,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.026</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index a7a4d1b469..6bedeb57c5 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 a8e907a3b2..289b12c5a1 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/b732e3c02/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 6c76e6794e..21c6d9cf76 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/b732e3c02/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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 6c62a30d00..7008dccbd4 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/b732e3c02/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L357">runtime.ts:357</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L376">runtime.ts:376</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L367">runtime.ts:367</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 5052b31e8a..213369f9c1 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/b732e3c02/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L299">runtime.ts:299</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L320">runtime.ts:320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L327">runtime.ts:327</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index e86ea282e9..92256de321 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/b732e3c02/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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 1a8377a19d..50a03de7a1 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/b732e3c02/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L50">runtime.ts:50</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L48">runtime.ts:48</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L77">runtime.ts:77</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L67">runtime.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L85">runtime.ts:85</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L96">runtime.ts:96</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L73">runtime.ts:73</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 20abe63288..2c4b2e1b74 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L957">runtime.ts:957</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 14ec13604d..ccba0814db 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/b732e3c02/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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 06abcd6ebb..a491671b2c 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L641">runtime.ts:641</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L687">runtime.ts:687</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 3533c94996..014a9aa89e 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/b732e3c02/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L401">runtime.ts:401</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L394">runtime.ts:394</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L553">runtime.ts:553</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 7a3339b3dc..3e460dfff3 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index a6017d3397..34da4b5e0f 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/b732e3c02/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 120d53fe47..98ba6ee167 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 94cae4ecd1..2af2845b83 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/b732e3c02/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index ff7b97bf61..19b58fbfe2 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index b71e7a3fc2..92eecd1df0 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index dac2ec6047..c879882057 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/b732e3c02/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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 0d5dcb98b7..69f539cc18 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/b732e3c02/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 510966227b..f3ad9d8ab3 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/b732e3c02/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L812">runtime.ts:812</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 47b880cf4c..f159629c7e 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/b732e3c02/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L339">runtime.ts:339</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L337">runtime.ts:337</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L340">runtime.ts:340</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 8a9934db2b..e46487ec93 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/b732e3c02/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index fece63381b..40bdb23ee5 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/b732e3c02/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index f0923bbbc7..96ede8fe67 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 1630883f3b..7a73792a7e 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b732e3c02/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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 2aaebee94e..7f8f48f484 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/b732e3c02/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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 7b046947aa..f5ccedb58e 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/b732e3c02/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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/b732e3c02/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a3b51f11b/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 b6fae5d3b6..7b95ed4f48 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 b4617ebd36..b9e3d20b4d 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
... 784 lines suppressed ...