You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/11/08 19:12:56 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@b807613c794321bf4fa765df026b1c3b454811b3)
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 9bddb44023 deploying docs (apache/tvm@b807613c794321bf4fa765df026b1c3b454811b3)
9bddb44023 is described below
commit 9bddb440236f99e3bf094ff8050123a373157ce2
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Nov 8 19:12:49 2022 +0000
deploying docs (apache/tvm@b807613c794321bf4fa765df026b1c3b454811b3)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 282079 -> 327199 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22031 -> 22934 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1724 ++++++++++----------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 78 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 78 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 61 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
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 | 17 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 33 +-
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 | 40 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1720 ++++++++++---------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 78 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 78 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 267 ++-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
126 files changed, 2567 insertions(+), 2796 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index d501408c74..9acba7fd3b 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 12aef69638..fb0f49ab60 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 f4b3b4c0ad..e9f6b4bb31 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 26.741 seconds)
+ **Total running time of the script:** ( 1 minutes 14.319 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 aefab5b8b8..bee994ddbb 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 965ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 959ms/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 a4dcc560df..e74fde61e4 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipbdb840dc-a02e-459b-b71d-cb7f50bcce26 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipdfe62a7a-981d-4de5-9f39-5cf27e7656f3 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 51db4caae2..908a49b293 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 40.1MB/s]
24%|##4 | 10.2M/41.5M [00:00<00:00, 35.5MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 34.6MB/s]
42%|####2 | 17.6M/41.5M [00:00<00:00, 31.4MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 34.1MB/s]
62%|######1 | 25.6M/41.5M [00:00<00:00, 32.3MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.7MB/s]
90%|########9 | 37.2M/41.5M [00:01<00:00, 36.6MB/s]
99%|#########9| 41.2M/41.5M [00:01<00:00, 38.0MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 36.2MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 45.7MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 53.2MB/s]
47%|####7 | 19.6M/41.5M [00:00<00:00, 48.4MB/s]
59%|#####8 | 24.3M/41.5M [00:00<00:00, 43.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 48.8MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 41.0MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 44.7MB/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 be52b4e83d..100c2af5f6 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
12%|#1 | 5.18M/44.7M [00:00<00:00, 46.2MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 126MB/s]
81%|########1 | 36.4M/44.7M [00:00<00:00, 115MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 108MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
55%|#####4 | 24.5M/44.7M [00:00<00:00, 108MB/s]
78%|#######8 | 34.9M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 3a294db396..254a528ef5 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 14.490 seconds)
+ **Total running time of the script:** ( 1 minutes 15.048 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 a717c604fe..cfde3582e0 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
=================
-**07:11.205** total execution time for **how_to_compile_models** files:
+**05:55.117** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 02:26.741 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:15.048 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:14.490 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:14.319 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.272 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.494 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.770 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.489 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:32.392 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.793 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:28.414 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.199 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.854 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.517 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.370 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.481 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.399 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.375 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.502 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.402 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 69122f8bb5..7b7207670c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7911 15.8094 15.9672 15.6082 0.1131
+ 17.0029 16.8330 19.0178 15.9217 0.9652
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 8dbad3b58b..e806091bf5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:02, 63.8MB/s]
9%|9 | 16.0M/170M [00:00<00:01, 83.1MB/s]
19%|#8 | 32.0M/170M [00:00<00:01, 108MB/s]
28%|##8 | 48.0M/170M [00:00<00:01, 125MB/s]
35%|###5 | 59.8M/170M [00:00<00:01, 104MB/s]
41%|####1 | 70.1M/170M [00:00<00:01, 97.0MB/s]
47%|####6 | 79.5M/170M [00:00<00:00, 95.2MB/s]
52%|#####2 | 88.7M/170M [00:01<00:01, 75.2MB/s]
59%|#####9 | 101M/170M [00:01<00:00, 88.0MB/s]
66%|######5 | 112M/170M [00:01<00:00, 91.5MB/s]
74%|#######4 | 126M/170M [00:01<00:00, 103MB/s]
80%|######## | 137M/170M [00:01<00:00, 85.6MB/s]
86%|########5 | 145M/170M [00:01<00:00, 74.9MB/s]
99%|#########8| 168M/170M [00:01<00:00, 111MB/s]
100%|##########| 170M/170M [00:01<00:00, 96.2MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
7%|6 | 11.6M/170M [00:00<00:01, 122MB/s]
14%|#3 | 23.2M/170M [00:00<00:01, 121MB/s]
20%|## | 34.8M/170M [00:00<00:01, 101MB/s]
27%|##7 | 46.7M/170M [00:00<00:01, 109MB/s]
34%|###3 | 57.4M/170M [00:00<00:01, 103MB/s]
40%|###9 | 67.4M/170M [00:00<00:01, 102MB/s]
46%|####5 | 77.7M/170M [00:00<00:00, 104MB/s]
52%|#####1 | 87.7M/170M [00:00<00:00, 103MB/s]
57%|#####7 | 97.6M/170M [00:01<00:00, 90.5MB/s]
65%|######5 | 111M/170M [00:01<00:00, 105MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 99.3MB/s]
77%|#######7 | 131M/170M [00:01<00:00, 101MB/s]
84%|########3 | 142M/170M [00:01<00:00, 103MB/s]
90%|########9 | 152M/170M [00:01<00:00, 96.2MB/s]
95%|#########5| 162M/170M [00:01<00:00, 88.9MB/s]
100%|##########| 170M/170M [00:01<00:00, 101MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 10.296 seconds)
+ **Total running time of the script:** ( 3 minutes 13.009 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 a96792db7a..721d28a976 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 42.8MB/s]
90%|########9 | 12.2M/13.6M [00:00<00:00, 33.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 37.7MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
60%|#####9 | 8.12M/13.6M [00:00<00:00, 84.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 104MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.1637 90.0786 91.2555 89.9017 0.2564
+ 90.3124 90.2312 92.6501 90.0818 0.2875
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.283 seconds)
+ **Total running time of the script:** ( 1 minutes 7.208 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 0d754f4f79..6c7052b2ef 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.9897 118.8924 125.5482 117.7585 0.8257
+ 121.2563 121.2194 122.6003 120.3327 0.3435
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 20.966 seconds)
+ **Total running time of the script:** ( 2 minutes 24.948 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 9e24fe014c..22017da9be 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 35.435 seconds)
+ **Total running time of the script:** ( 1 minutes 25.179 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 d8f1fdcb21..7f70337d06 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
2%|2 | 3296/132723 [00:00<00:06, 21215.21KB/s]
7%|7 | 9462/132723 [00:00<00:03, 40588.16KB/s]
12%|#1 | 15680/132723 [00:00<00:02, 42092.50KB/s]
15%|#5 | 20118/132723 [00:00<00:03, 34298.50KB/s]
21%|##1 | 27985/132723 [00:00<00:02, 46482.88KB/s]
26%|##6 | 34630/132723 [00:00<00:01, 52107.97KB/s]
32%|###2 | 42510/132723 [00:00<00:01, 59767.24KB/s]
37%|###7 | 49140/132723 [00:01<00:01, 52715.75KB/s]
43%|####2 | 56617/132723 [00:01<00:01, 58492.29KB/s]
48%|####8 | 64310/132723 [00:01<00:01, 60902.87KB/s]
53%|#####3 | 70685/132723 [00:01<00:01, 56202.94KB/s]
59%|#####9 | 78731/132723 [00:01<00:00, 62539.33KB/s]
64%|######4 | 85256/132723 [00:01<00:00, 53806.36KB/s]
70%|####### | 93182/132723 [00:01<00:00, 60122.63KB/s]
75%|#######5 | 99588/132723 [00:01<00:00, 46841.54KB/s]
81%|######## |
107505/132723 [00:02<00:00, 54037.64KB/s]
86%|########6 | 114654/132723 [00:02<00:00, 58247.57KB/s]
91%|#########1| 121093/132723 [00:02<00:00, 47438.23KB/s]
97%|#########7| 129116/132723 [00:02<00:00, 54817.26KB/s]
100%|##########| 132723/132723 [00:02<00:00, 52843.12KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5259/132723 [00:00<00:02, 52583.78KB/s]
10%|9 | 12778/132723 [00:00<00:01, 65872.72KB/s]
15%|#5 | 20561/132723 [00:00<00:01, 71329.31KB/s]
22%|##1 | 28557/132723 [00:00<00:01, 74734.53KB/s]
27%|##7 | 36479/132723 [00:00<00:01, 76350.57KB/s]
33%|###3 | 44339/132723 [00:00<00:01, 77113.67KB/s]
39%|###9 | 52283/132723 [00:00<00:01, 77867.27KB/s]
45%|####5 | 60213/132723 [00:00<00:00, 78318.01KB/s]
51%|#####1 | 68115/132723 [00:00<00:00, 78533.72KB/s]
57%|#####7 | 75987/132723 [00:01<00:00, 78589.28KB/s]
63%|######3 | 83883/132723 [00:01<00:00, 78700.80KB/s]
69%|######9 | 91781/132723 [00:01<00:00, 78784.26KB/s]
75%|#######5 | 99660/132723 [00:01<00:00, 78763.56KB/s]
81%|########1 | 107537/132723 [00:01<00:00, 78077.76KB/s]
87%|########6 | 115347/132723 [00:01<00:00, 77481.75KB/s]
93%|#########
2| 123101/132723 [00:01<00:00, 77497.21KB/s]
99%|#########8| 131035/132723 [00:01<00:00, 78038.43KB/s]
100%|##########| 132723/132723 [00:01<00:00, 76850.12KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 59.141 seconds)
+ **Total running time of the script:** ( 3 minutes 1.623 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 80375bb729..8348cd65fc 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:36.200** total execution time for **how_to_deploy_models** files:
+**12:38.418** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:10.296 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:13.009 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:59.141 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:01.623 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:20.966 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:24.948 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:35.435 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:25.179 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.283 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.208 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.759 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.920 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.916 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.033 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.397 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.491 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index f6e2065fbf..b011de1056 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip5c654c38-96ec-4c46-a8a9-7b73df95dd6a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip76f61c28-5c50-4565-9f8f-60f0d9db841f 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 833b4d216c..631b27306f 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
=================
-**00:49.782** total execution time for **how_to_extend_tvm** files:
+**00:46.505** 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``) | 00:46.325 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.072 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.393 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.401 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.057 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.024 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 6ddeb20fca..be4ea9998a 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6665us [6665us] (46.51%; 46.51%)
- FoldScaleAxis: 7667us [6us] (53.49%; 53.49%)
- FoldConstant: 7661us [1523us] (53.45%; 99.93%)
- InferType: 6138us [6138us] (42.83%; 80.12%)
+ InferType: 7241us [7241us] (47.69%; 47.69%)
+ FoldScaleAxis: 7941us [6us] (52.31%; 52.31%)
+ FoldConstant: 7935us [1632us] (52.27%; 99.93%)
+ InferType: 6303us [6303us] (41.51%; 79.43%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6160us [6160us] (44.74%; 44.74%)
- FoldScaleAxis: 7609us [5us] (55.26%; 55.26%)
- FoldConstant: 7604us [1535us] (55.23%; 99.94%)
- InferType: 6069us [6069us] (44.08%; 79.81%)
+ InferType: 6366us [6366us] (44.64%; 44.64%)
+ FoldScaleAxis: 7895us [5us] (55.36%; 55.36%)
+ FoldConstant: 7890us [1648us] (55.33%; 99.94%)
+ InferType: 6242us [6242us] (43.77%; 79.11%)
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 d861fd376a..1f88dc6be5 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.154079 ms
+ Convolution: 39.971710 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 c8ac23190a..573599d44a 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -659,7 +659,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.472153 ms
+ conv2d with tensor core: 13.361130 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 d6fe486ed2..c46a1e0a53 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018238
- Baseline: 3.440224
+ Numpy running time: 0.018666
+ Baseline: 3.201057
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.300349
+ Opt1: 0.293776
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335285
+ Opt2: 0.339217
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116285
+ Opt3: 0.117332
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108824
+ Opt4: 0.109443
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111008
+ Opt5: 0.111131
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147327
+ Opt6: 0.148696
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 470c9e6f45..251e2ffa14 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.010** total execution time for **how_to_optimize_operators** files:
+**00:34.436** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.352 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.745 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.515 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.538 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.143 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.152 | 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 f1c620a6ce..ac68297927 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
=================
-**09:49.553** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:11.042** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:17.110 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:39.665 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:34.085 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:05.348 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.288 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.640 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.315 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.831 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.228 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.059 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.461 | 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 3f9d59edc1..9d249fff89 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
@@ -206,13 +206,6 @@ file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- .T
-
-
@@ -247,12 +240,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [28], [], scope="local")[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -266,463 +259,421 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((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)]))
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_1: int32 = (rc.outer.outer*36)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[(threadIdx.x_1*3)] = @tir.if_then_else((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (0 < floormod(threadIdx.x_1, 3))), data[(((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)), data[(((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (floormod(threadIdx.x_1, 3) < 2)), data[(((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 52), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 168)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 2), 27)) && (floormod((threadIdx.x_1 + 2), 27) < 24)) && (1 < floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 169)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 2), 27)) && (floormod((threadIdx.x_1 + 2), 27) < 24)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 170)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 2), 27)) && (floormod((threadIdx.x_1 + 2), 27) < 24)) && (1 < floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ for (i2.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
}
}
}
@@ -778,7 +729,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.363 ms
+ Execution time of this operator: 0.304 ms
@@ -827,35 +778,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=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_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=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=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)
@@ -875,12 +826,12 @@ 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=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=3)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -900,10 +851,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[28];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -918,411 +869,396 @@ 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) {
- __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);
- }
- 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);
- }
- 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)]));
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 3)] = ((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = ((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 52) {
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 168)] = (((((3 <= ((((int)threadIdx.x) + 2) % 27)) && (((((int)threadIdx.x) + 2) % 27) < 24)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 169)] = (((((3 <= ((((int)threadIdx.x) + 2) % 27)) && (((((int)threadIdx.x) + 2) % 27) < 24)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 170)] = (((((3 <= ((((int)threadIdx.x) + 2) % 27)) && (((((int)threadIdx.x) + 2) % 27) < 24)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
}
}
- 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 < 4; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1385,7 +1321,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 17.110 seconds)
+ **Total running time of the script:** ( 5 minutes 39.665 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 7c41fdef8e..41d1ef5b5b 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2274 8.2274 8.2385 8.2162 0.0091
+ 8.2366 8.2315 8.2469 8.2313 0.0073
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.348 seconds)
+ **Total running time of the script:** ( 1 minutes 4.288 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 99a3766a0b..32be875bed 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 753.7040 754.1751 754.5343 752.4026 0.9319
+ 754.6781 753.9550 756.2006 753.8788 1.0770
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.564 seconds)
+ **Total running time of the script:** ( 1 minutes 34.085 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 bcb7bef393..4c8905d166 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,78 +386,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
+ for (i.outer.inner: int32, 0, 8) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 64) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -513,7 +467,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.866 ms
+ Execution time of this operator: 1.518 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 360343236a..837fe765a9 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:25.299** total execution time for **how_to_tune_with_autotvm** files:
+**00:26.758** 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``) | 00:25.263 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:26.723 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 2fc4ea06ee..edba3033c0 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -265,8 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 63.15/63.15 result: MeasureResult(costs=(0.003665625142857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8789360523223877, timestamp=1667871847.9924874) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2915996
- No: 2 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -388,8 +387,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2790347
- No: 3 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,930047
+ No: 2 GFLOPS: 12.05/12.05 result: MeasureResult(costs=(0.019211337999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.786815881729126, timestamp=1667929579.0447943) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,640704
+ No: 3 GFLOPS: 0.00/12.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -511,8 +511,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9309823
- No: 4 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7699149
+ No: 4 GFLOPS: 35.32/35.32 result: MeasureResult(costs=(0.0065546979375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.174964427947998, timestamp=1667929580.6686113) [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('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', 512), ('unroll_explicit', 1)],None,8523364
+ No: 5 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -634,8 +635,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10365241
- No: 5 GFLOPS: 0.00/63.15 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, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2680243
+ No: 6 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -757,8 +758,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,611541
- No: 6 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9798808
+ No: 7 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -880,8 +881,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8902723
- No: 7 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,331574
+ No: 8 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,8 +1004,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5962142
- No: 8 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1373334
+ No: 9 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,8 +1127,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3217062
- No: 9 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4883939
+ No: 10 GFLOPS: 80.29/80.29 result: MeasureResult(costs=(0.002883404388888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9578070640563965, timestamp=1667929585.974) [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7269055
+ No: 11 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,8 +1251,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10245233
- No: 10 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,308398
+ No: 12 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1372,8 +1374,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9666364
- No: 11 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5932193
+ No: 13 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1495,8 +1497,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10022506
- No: 12 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6763803
+ No: 14 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1618,8 +1620,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1531370
- No: 13 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5586598
+ No: 15 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1741,8 +1743,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6747722
- No: 14 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8335410
+ No: 16 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1864,9 +1866,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4113806
- No: 15 GFLOPS: 6.84/63.15 result: MeasureResult(costs=(0.03384215925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7952816486358643, timestamp=1667871854.1375206) [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2612672
- No: 16 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2182952
+ No: 17 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1988,8 +1989,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8967516
- No: 17 GFLOPS: 0.00/63.15 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, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9855387
+ No: 18 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2111,8 +2112,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2836766
- No: 18 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1970282
+ No: 19 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2234,9 +2235,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4434408
- No: 19 GFLOPS: 36.41/63.15 result: MeasureResult(costs=(0.006358260125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2706403732299805, timestamp=1667871855.6317317) [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6919947
- No: 20 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4287496
+ No: 20 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2358,7 +2358,7 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9590006
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8314704
@@ -2413,9 +2413,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2915996
+ [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7269055
Finish loading 20 records
- Time cost of this operator: 0.001870
+ Time cost of this operator: 0.001537
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 23ae5f8c37..53e0e46f92 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.9 98.752 (1, 2, 10, 10, 3) 2 1 [316.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.941 (1, 6, 10, 10) 1 1 [3.021]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.307 (1, 1, 10, 10, 3) 1 1 [0.984]
- Total_time - 320.905 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.4 98.713 (1, 2, 10, 10, 3) 2 1 [312.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.085 0.975 (1, 6, 10, 10) 1 1 [3.085]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.989 0.313 (1, 1, 10, 10, 3) 1 1 [0.989]
+ Total_time - 316.474 - - - - -
@@ -394,10 +394,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.4 97.516 (1, 6, 10, 10, 1) 2 1 [103.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.792 1.69 (1, 6, 10, 10) 1 1 [1.792]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.794 (1, 3, 10, 10, 1) 1 1 [0.842]
- Total_time - 106.034 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.5 97.925 (1, 6, 10, 10, 1) 2 1 [134.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.877 1.366 (1, 6, 10, 10) 1 1 [1.877]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.709 (1, 1, 10, 10, 3) 1 1 [0.974]
+ Total_time - 137.35 - - - - -
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 c0d9d411f2..6be1b66eb4 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp2liubq2r/images/random'
+ '/tmp/tmp_ifu4zvj/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp2liubq2r/images/target contains 8144 images
- /tmp/tmp2liubq2r/images/random contains 5000 images
+ /tmp/tmp_ifu4zvj/images/target contains 8144 images
+ /tmp/tmp_ifu4zvj/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2407 - accuracy: 0.9184 - val_loss: 0.1110 - val_accuracy: 0.9626 - 47s/epoch - 143ms/step
+ 328/328 - 46s - loss: 0.2264 - accuracy: 0.9224 - val_loss: 0.2056 - val_accuracy: 0.9282 - 46s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.1017 - accuracy: 0.9624 - val_loss: 0.0952 - val_accuracy: 0.9660 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.1044 - accuracy: 0.9598 - val_loss: 0.0932 - val_accuracy: 0.9690 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0678 - accuracy: 0.9735 - val_loss: 0.2055 - val_accuracy: 0.9279 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0682 - accuracy: 0.9746 - val_loss: 0.0979 - val_accuracy: 0.9679 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7efd751fb490>
+ <keras.callbacks.History object at 0x7fe5f02e7f10>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 32.531 seconds)
+ **Total running time of the script:** ( 4 minutes 19.422 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 f8468b6da5..daa9388303 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**05:33.660** total execution time for **how_to_work_with_microtvm** files:
+**05:21.859** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:32.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:19.422 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.988 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.837 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.655 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.721 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.792 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 7680eef71c..b9c81e3668 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.899** total execution time for **how_to_work_with_relay** files:
+**00:43.995** 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``) | 00:32.221 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.900 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.089 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.313 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.581 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.775 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 21f7895231..cbb3d99d6c 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7efdce4144d0>
+ <function my_cuda_math_rule at 0x7fe5929f2830>
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 aea9a47f41..9ce00dad23 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:06.481** total execution time for **how_to_work_with_schedules** files:
+**00:04.910** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.153 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.387 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.993 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.169 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.570 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.577 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.566 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.120 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.054 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 2222046ca7..584d9cc15d 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpxpc6rtyo/input0.cc'\nsource_filename = \"/tmp/tmpxpc6rtyo/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpisxaqdoi/input0.cc'\nsource_filename = \"/tmp/tmpisxaqdoi/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index d12c10c8d3..59e19b6986 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:26.921** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.740** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.915 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.734 | 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 fc59ed8752..1fecc103f2 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 31.21s!
+ resnet18_v1 inference graph built in 28.67s!
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 243ab27c3f..fb294ff926 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 20.85s!
+ yolov3-tiny inference graph built in 19.46s!
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 da02d9f1d1..174cffe89f 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
=================
-**01:44.499** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.427** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:53.275 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.776 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.224 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.651 | 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 d7d88c01f1..7690cccb0c 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
=================
-**00:03.423** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.090** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.969 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.634 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.455 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.456 | 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 7b02fbf90b..58da792608 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
=================
-**00:00.791** total execution time for **topic_vta_tutorials** files:
+**00:00.812** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.422 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.436 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.370 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.376 | 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 24df30e058..5b312f6985 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E
+
+
@@ -326,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.971 ms
+ Execution time of this operator: 94.445 ms
@@ -444,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 25.906 seconds)
+ **Total running time of the script:** ( 1 minutes 35.299 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 8ac74e4c0e..8da500fc0d 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 1.76/1.76 result: MeasureResult(costs=(0.15216853219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.588067054748535, timestamp=1667870407.7993975) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
- No: 2 GFLOPS: 4.30/4.30 result: MeasureResult(costs=(0.0624862162,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2039549350738525, timestamp=1667870409.003014) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
- No: 3 GFLOPS: 10.81/10.81 result: MeasureResult(costs=(0.0248387668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5392439365386963, timestamp=1667870410.3107543) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
- No: 4 GFLOPS: 9.47/10.81 result: MeasureResult(costs=(0.0283396608,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6711032390594482, timestamp=1667870411.660674) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
- No: 5 GFLOPS: 2.75/10.81 result: MeasureResult(costs=(0.0977128568,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7126760482788086, timestamp=1667870413.5966527) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
- No: 6 GFLOPS: 3.01/10.81 result: MeasureResult(costs=(0.08909641,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.587338924407959, timestamp=1667870415.1883016) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
- No: 7 GFLOPS: 0.94/10.81 result: MeasureResult(costs=(0.2842348806,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.706167459487915, timestamp=1667870420.6292396) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
- No: 8 GFLOPS: 9.66/10.81 result: MeasureResult(costs=(0.027790581800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7444319725036621, timestamp=1667870421.2817755) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
- No: 9 GFLOPS: 2.40/10.81 result: MeasureResult(costs=(0.1120682792,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9104909896850586, timestamp=1667870423.527031) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
- No: 10 GFLOPS: 9.15/10.81 result: MeasureResult(costs=(0.029330837600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8099238872528076, timestamp=1667870424.164117) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+ No: 1 GFLOPS: 0.49/0.49 result: MeasureResult(costs=(0.5436071125999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.832136392593384, timestamp=1667928192.2193973) [('tile_y', [-1, 512]), ('tile_x', [-1, 1])],None,9
+ No: 2 GFLOPS: 0.51/0.51 result: MeasureResult(costs=(0.5277764916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.560190200805664, timestamp=1667928201.5797062) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
+ No: 3 GFLOPS: 13.84/13.84 result: MeasureResult(costs=(0.0193974372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.496504545211792, timestamp=1667928202.7938218) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+ No: 4 GFLOPS: 1.52/13.84 result: MeasureResult(costs=(0.176035852,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.965695381164551, timestamp=1667928206.525283) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+ No: 5 GFLOPS: 0.51/13.84 result: MeasureResult(costs=(0.527366442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.58648157119751, timestamp=1667928215.2718334) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+ No: 6 GFLOPS: 10.77/13.84 result: MeasureResult(costs=(0.024925931800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5907962322235107, timestamp=1667928215.8398972) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
+ No: 7 GFLOPS: 1.77/13.84 result: MeasureResult(costs=(0.1518953626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.578155755996704, timestamp=1667928218.4322212) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+ No: 8 GFLOPS: 3.71/13.84 result: MeasureResult(costs=(0.0724365372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3622841835021973, timestamp=1667928219.8061028) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+ No: 9 GFLOPS: 13.56/13.84 result: MeasureResult(costs=(0.019802845,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.43721771240234375, timestamp=1667928220.3544896) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
+ No: 10 GFLOPS: 10.01/13.84 result: MeasureResult(costs=(0.0268292798,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5377368927001953, timestamp=1667928220.9470682) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 053d0fb346..d604d7889e 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 510.6892897400006, 'median': 510.96751540000014, 'std': 1.8923402940276843}
+ {'mean': 513.2742928301741, 'median': 513.4689666498161, 'std': 1.5081723780732224}
@@ -554,31 +554,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 23.93/ 23.93 GFLOPS | Progress: (4/20) | 7.63 s
[Task 1/25] Current/Best: 9.46/ 23.93 GFLOPS | Progress: (8/20) | 11.28 s
[Task 1/25] Current/Best: 19.36/ 23.93 GFLOPS | Progress: (12/20) | 12.85 s
[Task 1/25] Current/Best: 14.74/ 23.93 GFLOPS | Progress: (16/20) | 18.71 s
[Task 1/25] Current/Best: 23.15/ 23.93 GFLOPS | Progress: (20/20) | 20.80 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.00/ 18.92 GFLOPS | Progress: (4/20) | 3.00 s
[Task 2/25] Current/Best: 14.06/ 18.92 GFLOPS | Progress: (8/20) | 4.63 s
[Task 2/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (12/20) | 6.23 s
[Task 2/25] Current/Best: 9.02/ 20.08 GFLOPS | Progress: (16/20) | 7.90 s
[Task 2/25] Current/Best: 17.88/ 20.08 GFLOPS | Progress: (20/20) | 9.54 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 19.53/ 19.53 GFLOPS | Progress: (4/20) | 3.88 s
[Task 3/25] Current/Best: 8.21/ 19.53 GFLOPS | Progress: (8/20) | 7.81 s
[Task 3/25] Current/Best: 9.44/ 19.53 GFLOPS | Progress: (12/20) | 10.41 s
[Task 3/25] Current/Best: 8.11/ 19.53 GFLOPS | Progress: (16/20) | 12.72 s
[Task 3/25] Current/Best: 16.55/ 19.53 GFLOPS | Progress: (20/20) | 15.85 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (4/20) | 7.74 s
[Task 4/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (8/20) | 9.73 s
[Task 4/25] Current/Best: 14.55/ 23.06 GFLOPS | Progress: (12/20) | 12.00 s
[Task 4/25] Current/Best: 4.78/ 23.06 GFLOPS | Progress: (16/20) | 13.82 s
[Task 4/25] Current/Best: 13.19/ 23.06 GFLOPS | Progress: (20/20) | 16.07 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 14.50/ 21.95 GFLOPS | Progress: (4/20) | 3.03 s
[Task 5/25] Current/Best: 13.08/ 21.95 GFLOPS | Progress: (8/20) | 5.29 s
[Task 5/25] Current/Best: 22.76/ 22.76 GFLOPS | Progress: (12/20) | 7.42 s
[Task 5/25] Current/Best: 9.66/ 22.76 GFLOPS | Progress: (16/20) | 9.62 s
[Task 5/25] Current/Best: 13.64/ 22.76 GFLOPS | Progress: (20/20) | 12.03 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.94/ 14.33 GFLOPS | Progress: (4/20) | 4.72 s
[Task 6/25] Current/Best: 9.62/ 14.33 GFLOPS | Progress: (8/20) | 6.88 s
[Task 6/25] Current/Best: 8.12/ 18.17 GFLOPS | Progress: (12/20) | 8.91 s
[Task 6/25] Current/Best: 19.09/ 19.09 GFLOPS | Progress: (16/20) | 11.28 s
[Task 6/25] Current/Best: 14.31/ 19.47 GFLOPS | Progress: (20/20) | 14.19 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.04/ 15.97 GFLOPS | Progress: (4/20) | 3.55 s
[Task 7/25] Current/Best: 12.56/ 19.71 GFLOPS | Progress: (8/20) | 5.38 s
[Task 7/25] Current/Best: 5.04/ 19.71 GFLOPS | Progress: (12/20) | 7.47 s
[Task 7/25] Current/Best: 15.12/ 19.71 GFLOPS | Progress: (16/20) | 9.65 s
[Task 7/25] Current/Best: 16.83/ 19.71 GFLOPS | Progress: (20/20) | 11.26 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 13.95/ 13.95 GFLOPS | Progress: (4/20) | 4.46 s
[Task 8/25] Current/Best: 11.13/ 13.95 GFLOPS | Progress: (8/20) | 16.00 s
[Task 8/25] Current/Best: 10.05/ 17.10 GFLOPS | Progress: (12/20) | 18.09 s
[Task 8/25] Current/Best: 7.29/ 17.10 GFLOPS | Progress: (16/20) | 21.59 s
[Task 8/25] Current/Best: 9.94/ 17.10 GFLOPS | Progress: (20/20) | 28.64 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.96/ 19.84 GFLOPS | Progress: (4/20) | 4.09 s
[Task 9/25] Current/Best: 11.39/ 19.84 GFLOPS | Progress: (8/20) | 7.80 s
[Task 9/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (12/20) | 12.62 s
[Task 9/25] Current/Best: 7.67/ 20.69 GFLOPS | Progress: (16/20) | 15.47 s
[Task 9/25] Current/Best: 19.67/ 20.69 GFLOPS | Progress: (20/20) | 26.36 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.14/ 19.27 GFLOPS | Progress: (4/20) | 3.91 s
[Task 10/25] Current/Best: 6.84/ 19.27 GFLOPS | Progress: (8/20) | 5.26 s
[Task 10/25] Current/Best: 9.11/ 19.27 GFLOPS | Progress: (12/20) | 6.81 s
[Task 10/25] Current/Best: 14.49/ 19.27 GFLOPS | Progress: (16/20) | 9.34 s
[Task 10/25] Current/Best: 4.30/ 19.27 GFLOPS | Progress: (20/20) | 12.08 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.41/ 11.43 GFLOPS | Progress: (4/20) | 4.27 s
[Task 11/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (8/20) | 7.60 s
[Task 11/25] Current/Best: 18.59/ 21.72 GFLOPS | Progress: (12/20) | 9.13 s
[Task 11/25] Current/Best: 16.40/ 21.72 GFLOPS | Progress: (16/20) | 11.01 s
[Task 11/25] Current/Best: 14.39/ 21.72 GFLOPS | Progress: (20/20) | 12.99 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 18.17/ 18.17 GFLOPS | Progress: (4/20) | 5.27 s
[Task 12/25] Current/Best: 9.73/ 20.25 GFLOPS | Progress: (8/20) | 8.81 s
[Task 12/25] Current/Best: 5.50/ 20.25 GFLOPS | Progress: (12/20) | 10.94 s
[Task 12/25] Current/Best: 9.66/ 20.25 GFLOPS | Progress: (16/20) | 13.67 s
[Task 12/25] Current/Best: 20.42/ 20.42 GFLOPS | Progress: (20/20) | 21.98 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.08/ 14.94 GFLOPS | Progress: (4/20) | 3.75 s
[Task 13/25] Current/Best: 20.00/ 22.16 GFLOPS | Progress: (8/20) | 5.70 s
[Task 13/25] Current/Best: 17.29/ 22.16 GFLOPS | Progress: (12/20) | 9.54 s
[Task 13/25] Current/Best: 21.14/ 22.16 GFLOPS | Progress: (16/20) | 11.57 s
[Task 13/25] Current/Best: 19.69/ 22.16 GFLOPS | Progress: (20/20) | 14.63 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 8.27/ 14.30 GFLOPS | Progress: (4/20) | 3.50 s
[Task 14/25] Current/Best: 9.43/ 14.30 GFLOPS | Progress: (8/20) | 10.24 s
[Task 14/25] Current/Best: 16.59/ 16.59 GFLOPS | Progress: (12/20) | 13.60 s
[Task 14/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (16/20) | 16.99 s
[Task 14/25] Current/Best: 11.65/ 20.62 GFLOPS | Progress: (20/20) | 20.89 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 3.11/ 21.02 GFLOPS | Progress: (4/20) | 4.68 s
[Task 15/25] Current/Best: 14.60/ 21.02 GFLOPS | Progress: (8/20) | 6.07 s
[Task 15/25] Current/Best: 15.98/ 21.02 GFLOPS | Progress: (12/20) | 7.24 s Done.
-
[Task 15/25] Current/Best: 18.48/ 21.02 GFLOPS | Progress: (16/20) | 9.34 s
[Task 15/25] Current/Best: 12.30/ 21.02 GFLOPS | Progress: (20/20) | 11.83 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.25/ 19.25 GFLOPS | Progress: (4/20) | 3.50 s
[Task 16/25] Current/Best: 17.49/ 19.96 GFLOPS | Progress: (8/20) | 4.99 s
[Task 16/25] Current/Best: 17.25/ 19.96 GFLOPS | Progress: (12/20) | 6.90 s
[Task 16/25] Current/Best: 5.67/ 19.96 GFLOPS | Progress: (16/20) | 8.98 s
[Task 16/25] Current/Best: 4.13/ 19.96 GFLOPS | Progress: (20/20) | 10.65 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 8.95/ 17.40 GFLOPS | Progress: (4/20) | 4.03 s
[Task 17/25] Current/Best: 18.01/ 18.01 GFLOPS | Progress: (8/20) | 6.76 s
[Task 17/25] Current/Best: 11.59/ 18.35 GFLOPS | Progress: (12/20) | 8.74 s
[Task 17/25] Current/Best: 5.16/ 21.08 GFLOPS | Progress: (16/20) | 10.90 s
[Task 17/25] Current/Best: 16.99/ 21.08 GFLOPS | Progress: (20/20) | 13.17 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.30/ 17.68 GFLOPS | Progress: (4/20) | 6.99 s
[Task 18/25] Current/Best: 4.33/ 17.68 GFLOPS | Progress: (8/20) | 10.82 s
[Task 18/25] Current/Best: 8.79/ 17.68 GFLOPS | Progress: (12/20) | 17.83 s
[Task 18/25] Current/Best: 9.59/ 19.31 GFLOPS | Progress: (16/20) | 21.34 s
[Task 18/25] Current/Best: 7.78/ 19.34 GFLOPS | Progress: (20/20) | 25.77 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.33/ 12.76 GFLOPS | Progress: (4/20) | 6.51 s
[Task 19/25] Current/Best: 8.37/ 19.06 GFLOPS | Progress: (8/20) | 10.04 s
[Task 19/25] Current/Best: 13.27/ 19.06 GFLOPS | Progress: (12/20) | 13.53 s
[Task 19/25] Current/Best: 9.74/ 19.06 GFLOPS | Progress: (16/20) | 16.47 s
[Task 19/25] Current/Best: 7.03/ 19.06 GFLOPS | Progress: (20/20) | 19.87 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 4.52/ 17.02 GFLOPS | Progress: (4/20) | 3.55 s
[Task 20/25] Current/Best: 4.99/ 19.55 GFLOPS | Progress: (8/20) | 5.41 s
[Task 20/25] Current/Best: 5.14/ 19.55 GFLOPS | Progress: (12/20) | 9.62 s
[Task 20/25] Current/Best: 13.06/ 19.55 GFLOPS | Progress: (16/20) | 12.07 s
[Task 20/25] Current/Best: 4.96/ 19.55 GFLOPS | Progress: (20/20) | 16.26 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 14.43/ 14.43 GFLOPS | Progress: (4/20) | 2.68 s
[Task 21/25] Current/Best: 10.62/ 16.52 GFLOPS | Progress: (8/20) | 4.70 s
[Task 21/25] Current/Best: 15.53/ 18.16 GFLOPS | Progress: (12/20) | 6.21 s
[Task 21/25] Current/Best: 8.50/ 18.16 GFLOPS | Progress: (16/20) | 8.25 s
[Task 21/25] Current/Best: 9.44/ 18.16 GFLOPS | Progress: (20/20) |
10.56 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 22/25] Current/Best: 12.54/ 16.80 GFLOPS | Progress: (4/20) | 4.93 s
[Task 22/25] Current/Best: 21.11/ 21.11 GFLOPS | Progress: (8/20) | 7.04 s
[Task 22/25] Current/Best: 11.57/ 21.11 GFLOPS | Progress: (12/20) | 9.40 s
[Task 22/25] Current/Best: 14.02/ 21.11 GFLOPS | Progress: (16/20) | 11.58 s
[Task 22/25] Current/Best: 8.76/ 21.11 GFLOPS | Progress: (20/20) | 14.33 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 7.67/ 22.71 GFLOPS | Progress: (4/20) | 3.74 s
[Task 23/25] Current/Best: 10.84/ 22.71 GFLOPS | Progress: (8/20) | 5.86 s
[Task 23/25] Current/Best: 11.27/ 22.71 GFLOPS | Progress: (12/20) | 8.13 s
[Task 23/25] Current/Best: 9.48/ 22.71 GFLOPS | Progress: (16/20) | 10.50 s
[Task 23/25] Current/Best: 21.34/ 22.71 GFLOPS | Progress: (20/20) | 13.49 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.83/ 7.83 GFLOPS | Progress: (4/20) | 12.21 s
[Task 24/25] Current/Best: 10.24/ 10.34 GFLOPS | Progress: (8/20) | 23.77 s
[Task 24/25] Current/Best: 8.90/ 10.34 GFLOPS | Progress: (12/20) | 35.06 s
[Task 24/25] Current/Best: 2.54/ 10.34 GFLOPS | Progress: (16/20) | 46.69 s
[Task 24/25] Current/Best: 9.31/ 10.34 GFLOPS | Progress: (20/20) | 58.33 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 1.55/ 6.40 GFLOPS | Progress: (4/20) | 4.58 s
[Task 25/25] Current/Best: 6.43/ 8.25 GFLOPS | Progress: (8/20) | 6.59 s
[Task 25/25] Current/Best: 6.11/ 8.25 GFLOPS | Progress: (12/20) | 11.17 s
[Task 25/25] Current/Best: 1.55/ 8.25 GFLOPS | Progress: (16/20) | 21.92 s
[Task 25/25] Current/Best: 9.62/ 9.62 GFLOPS | Progress: (20/20) | 26.83 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 15.09/ 18.83 GFLOPS | Progress: (4/20) | 6.67 s
[Task 1/25] Current/Best: 17.07/ 18.83 GFLOPS | Progress: (8/20) | 11.12 s
[Task 1/25] Current/Best: 14.52/ 19.01 GFLOPS | Progress: (12/20) | 14.01 s
[Task 1/25] Current/Best: 22.82/ 22.82 GFLOPS | Progress: (16/20) | 16.12 s
[Task 1/25] Current/Best: 17.60/ 23.41 GFLOPS | Progress: (20/20) | 17.82 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 5.56/ 14.23 GFLOPS | Progress: (4/20) | 3.17 s
[Task 2/25] Current/Best: 5.69/ 19.71 GFLOPS | Progress: (8/20) | 4.51 s
[Task 2/25] Current/Best: 3.20/ 20.62 GFLOPS | Progress: (12/20) | 5.88 s
[Task 2/25] Current/Best: 5.09/ 20.62 GFLOPS | Progress: (16/20) | 7.19 s
[Task 2/25] Current/Best: 11.91/ 20.62 GFLOPS | Progress: (20/20) | 8.52 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 3.12/ 18.57 GFLOPS | Progress: (4/20) | 4.14 s
[Task 3/25] Current/Best: 7.09/ 18.57 GFLOPS | Progress: (8/20) | 6.29 s
[Task 3/25] Current/Best: 8.40/ 18.57 GFLOPS | Progress: (12/20) | 10.17 s
[Task 3/25] Current/Best: 15.91/ 18.57 GFLOPS | Progress: (16/20) | 13.97 s
[Task 3/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (20/20) | 16.06 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.56/ 12.56 GFLOPS | Progress: (4/20) | 3.33 s
[Task 4/25] Current/Best: 13.11/ 13.11 GFLOPS | Progress: (8/20) | 6.08 s
[Task 4/25] Current/Best: 6.66/ 13.67 GFLOPS | Progress: (12/20) | 8.55 s
[Task 4/25] Current/Best: 15.60/ 15.60 GFLOPS | Progress: (16/20) | 10.32 s
[Task 4/25] Current/Best: 13.58/ 16.93 GFLOPS | Progress: (20/20) | 12.81 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.27/ 22.82 GFLOPS | Progress: (4/20) | 3.22 s
[Task 5/25] Current/Best: 4.92/ 22.82 GFLOPS | Progress: (8/20) | 4.83 s
[Task 5/25] Current/Best: 16.53/ 22.82 GFLOPS | Progress: (12/20) | 6.81 s
[Task 5/25] Current/Best: 5.56/ 22.82 GFLOPS | Progress: (16/20) | 8.54 s
[Task 5/25] Current/Best: 3.08/ 22.82 GFLOPS | Progress: (20/20) | 10.54 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.72/ 15.23 GFLOPS | Progress: (4/20) | 3.87 s
[Task 6/25] Current/Best: 4.99/ 15.23 GFLOPS | Progress: (8/20) | 6.26 s
[Task 6/25] Current/Best: 10.08/ 15.23 GFLOPS | Progress: (12/20) | 8.52 s
[Task 6/25] Current/Best: 10.25/ 19.91 GFLOPS | Progress: (16/20) | 10.13 s
[Task 6/25] Current/Best: 3.07/ 19.91 GFLOPS | Progress: (20/20) | 13.17 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 19.61/ 19.61 GFLOPS | Progress: (4/20) | 3.37 s
[Task 7/25] Current/Best: 4.82/ 19.61 GFLOPS | Progress: (8/20) | 6.21 s
[Task 7/25] Current/Best: 11.98/ 19.61 GFLOPS | Progress: (12/20) | 7.99 s
[Task 7/25] Current/Best: 8.34/ 20.09 GFLOPS | Progress: (16/20) | 9.91 s
[Task 7/25] Current/Best: 15.21/ 20.09 GFLOPS | Progress: (20/20) | 12.40 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 3.63/ 18.25 GFLOPS | Progress: (4/20) | 7.14 s
[Task 8/25] Current/Best: 4.49/ 18.25 GFLOPS | Progress: (8/20) | 10.15 s
[Task 8/25] Current/Best: 14.35/ 18.25 GFLOPS | Progress: (12/20) | 15.26 s
[Task 8/25] Current/Best: 19.10/ 21.36 GFLOPS | Progress: (16/20) | 17.22 s
[Task 8/25] Current/Best: 7.98/ 21.36 GFLOPS | Progress: (20/20) | 19.77 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 21.74/ 21.74 GFLOPS | Progress: (4/20) | 5.57 s
[Task 9/25] Current/Best: 13.41/ 21.74 GFLOPS | Progress: (8/20) | 10.22 s
[Task 9/25] Current/Best: 6.06/ 21.74 GFLOPS | Progress: (12/20) | 17.90 s
[Task 9/25] Current/Best: 6.66/ 23.02 GFLOPS | Progress: (16/20) | 19.23 s
[Task 9/25] Current/Best: 3.24/ 23.02 GFLOPS | Progress: (20/20) | 21.48 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 14.56/ 19.02 GFLOPS | Progress: (4/20) | 3.14 s
[Task 10/25] Current/Best: 12.95/ 19.02 GFLOPS | Progress: (8/20) | 5.98 s
[Task 10/25] Current/Best: 16.21/ 19.02 GFLOPS | Progress: (12/20) | 8.44 s
[Task 10/25] Current/Best: 15.29/ 19.02 GFLOPS | Progress: (16/20) | 10.45 s
[Task 10/25] Current/Best: 19.50/ 19.50 GFLOPS | Progress: (20/20) | 12.50 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 22.78/ 22.78 GFLOPS | Progress: (4/20) | 3.54 s
[Task 11/25] Current/Best: 19.01/ 22.78 GFLOPS | Progress: (8/20) | 5.76 s
[Task 11/25] Current/Best: 19.73/ 22.78 GFLOPS | Progress: (12/20) | 7.87 s
[Task 11/25] Current/Best: 21.83/ 22.78 GFLOPS | Progress: (16/20) | 10.67 s
[Task 11/25] Current/Best: 7.14/ 22.78 GFLOPS | Progress: (20/20) | 13.07 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 16.51/ 18.52 GFLOPS | Progress: (4/20) | 4.21 s
[Task 12/25] Current/Best: 17.60/ 21.08 GFLOPS | Progress: (8/20) | 7.03 s
[Task 12/25] Current/Best: 4.80/ 21.08 GFLOPS | Progress: (12/20) | 9.49 s
[Task 12/25] Current/Best: 17.49/ 21.70 GFLOPS | Progress: (16/20) | 10.92 s
[Task 12/25] Current/Best: 15.30/ 21.70 GFLOPS | Progress: (20/20) | 13.56 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.50/ 17.50 GFLOPS | Progress: (4/20) | 5.00 s
[Task 13/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (8/20) | 7.26 s
[Task 13/25] Current/Best: 23.10/ 23.10 GFLOPS | Progress: (12/20) | 10.00 s
[Task 13/25] Current/Best: 17.40/ 23.10 GFLOPS | Progress: (16/20) | 12.15 s
[Task 13/25] Current/Best: 14.28/ 23.10 GFLOPS | Progress: (20/20) | 14.14 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 17.39/ 17.39 GFLOPS | Progress: (4/20) | 3.23 s
[Task 14/25] Current/Best: 2.38/ 17.39 GFLOPS | Progress: (8/20) | 7.17 s
[Task 14/25] Current/Best: 10.99/ 17.39 GFLOPS | Progress: (12/20) | 12.40 s
[Task 14/25] Current/Best: 12.49/ 17.39 GFLOPS | Progress: (16/20) | 14.26 s
[Task 14/25] Current/Best: 4.98/ 17.39 GFLOPS | Progress: (20/20) | 17.12 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 9.43/ 18.98 GFLOPS | Progress: (4/20) | 4.05 s
[Task 15/25] Current/Best: 16.90/ 18.98 GFLOPS | Progress: (8/20) | 5.25 s
[Task 15/25] Current/Best: 19.67/ 19.67 GFLOPS | Progress: (12/20) | 12.55 s
[Task 15/25] Current/Best: 13.86/ 19.67 GFLOPS | Progress: (16/20) | 14.09 s Done.
+
[Task 15/25] Current/Best: 9.67/ 19.67 GFLOPS | Progress: (20/20) | 17.27 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.72/ 14.72 GFLOPS | Progress: (4/20) | 3.91 s
[Task 16/25] Current/Best: 15.95/ 18.15 GFLOPS | Progress: (8/20) | 5.26 s
[Task 16/25] Current/Best: 14.99/ 21.20 GFLOPS | Progress: (12/20) | 6.45 s
[Task 16/25] Current/Best: 15.23/ 22.24 GFLOPS | Progress: (16/20) | 8.03 s
[Task 16/25] Current/Best: 5.36/ 22.24 GFLOPS | Progress: (20/20) | 10.25 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 19.13/ 22.85 GFLOPS | Progress: (4/20) | 4.06 s
[Task 17/25] Current/Best: 21.28/ 22.85 GFLOPS | Progress: (8/20) | 6.16 s
[Task 17/25] Current/Best: 12.10/ 22.85 GFLOPS | Progress: (12/20) | 8.10 s
[Task 17/25] Current/Best: 11.89/ 22.85 GFLOPS | Progress: (16/20) | 10.15 s
[Task 17/25] Current/Best: 3.09/ 22.85 GFLOPS | Progress: (20/20) | 12.75 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 3.04/ 12.57 GFLOPS | Progress: (4/20) | 5.61 s
[Task 18/25] Current/Best: 21.33/ 21.33 GFLOPS | Progress: (8/20) | 7.69 s
[Task 18/25] Current/Best: 22.01/ 22.01 GFLOPS | Progress: (12/20) | 9.46 s
[Task 18/25] Current/Best: 18.44/ 22.01 GFLOPS | Progress: (16/20) | 11.10 s
[Task 18/25] Current/Best: 17.04/ 22.01 GFLOPS | Progress: (20/20) | 12.55 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.68/ 18.72 GFLOPS | Progress: (4/20) | 3.85 s
[Task 19/25] Current/Best: 11.34/ 18.72 GFLOPS | Progress: (8/20) | 10.38 s
[Task 19/25] Current/Best: 12.40/ 19.31 GFLOPS | Progress: (12/20) | 12.28 s
[Task 19/25] Current/Best: 11.24/ 19.31 GFLOPS | Progress: (16/20) | 17.31 s
[Task 19/25] Current/Best: 6.51/ 19.31 GFLOPS | Progress: (20/20) | 19.78 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.92/ 18.64 GFLOPS | Progress: (4/20) | 3.63 s
[Task 20/25] Current/Best: 7.56/ 18.64 GFLOPS | Progress: (8/20) | 5.30 s
[Task 20/25] Current/Best: 13.03/ 18.64 GFLOPS | Progress: (12/20) | 8.68 s
[Task 20/25] Current/Best: 4.75/ 18.64 GFLOPS | Progress: (16/20) | 12.25 s
[Task 20/25] Current/Best: 17.66/ 18.64 GFLOPS | Progress: (20/20) | 14.99 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 13.69/ 13.69 GFLOPS | Progress: (4/20) | 3.37 s
[Task 21/25] Current/Best: 10.17/ 13.69 GFLOPS | Progress: (8/20) | 6.01 s
[Task 21/25] Current/Best: 15.72/ 19.89 GFLOPS | Progress: (12/20) | 8.09 s Done.
+
[Task 21/25] Current/Best: 19.17/ 19.89 GFLOPS | Progress: (16/20) | 10.64 s
[Task 21/25] Current/Best: 11.50/ 19.89 GFLOPS | Progress: (20/20) | 13.01 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.54/ 15.25 GFLOPS | Progress: (4/20) | 3.90 s
[Task 22/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (8/20) | 5.78 s
[Task 22/25] Current/Best: 2.66/ 18.23 GFLOPS | Progress: (12/20) | 7.75 s
[Task 22/25] Current/Best: 12.71/ 18.78 GFLOPS | Progress: (16/20) | 9.39 s
[Task 22/25] Current/Best: 6.94/ 18.78 GFLOPS | Progress: (20/20) | 13.00 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.52/ 13.19 GFLOPS | Progress: (4/20) | 5.35 s
[Task 23/25] Current/Best: 12.46/ 17.66 GFLOPS | Progress: (8/20) | 8.71 s
[Task 23/25] Current/Best: 22.41/ 22.41 GFLOPS | Progress: (12/20) | 10.94 s
[Task 23/25] Current/Best: 14.30/ 23.38 GFLOPS | Progress: (16/20) | 13.19 s
[Task 23/25] Current/Best: 1.55/ 23.38 GFLOPS | Progress: (20/20) | 16.70 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.67/ 4.00 GFLOPS | Progress: (4/20) | 12.29 s
[Task 24/25] Current/Best: 5.96/ 5.96 GFLOPS | Progress: (8/20) | 22.97 s
[Task 24/25] Current/Best: 3.69/ 5.96 GFLOPS | Progress: (12/20) | 34.59 s
[Task 24/25] Current/Best: 8.01/ 8.01 GFLOPS | Progress: (16/20) | 40.69 s
[Task 24/25] Current/Best: 9.98/ 10.19 GFLOPS | Progress: (20/20) | 51.20 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 1.54/ 8.00 GFLOPS | Progress: (4/20) | 12.25 s
[Task 25/25] Current/Best: 5.02/ 8.00 GFLOPS | Progress: (8/20) | 17.43 s
[Task 25/25] Current/Best: 8.36/ 8.36 GFLOPS | Progress: (12/20) | 18.81 s
[Task 25/25] Current/Best: 9.44/ 9.44 GFLOPS | Progress: (16/20) | 20.93 s
[Task 25/25] Current/Best: 1.55/ 9.44 GFLOPS | Progress: (20/20) | 31.63 s
@@ -674,8 +673,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 409.97064049000073, 'median': 409.4862530499995, 'std': 1.3765838115104683}
- unoptimized: {'mean': 510.6892897400006, 'median': 510.96751540000014, 'std': 1.8923402940276843}
+ optimized: {'mean': 395.1927164298104, 'median': 394.8172410000552, 'std': 1.0674296433254005}
+ unoptimized: {'mean': 513.2742928301741, 'median': 513.4689666498161, 'std': 1.5081723780732224}
@@ -756,7 +755,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 8.730 seconds)
+ **Total running time of the script:** ( 10 minutes 24.491 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 6f730e8dce..930a448304 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.256e-07 secs/op
+ 1.247e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d8c2f33e10..88a67ebb58 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xde69960)), stage(b, placeholder(b, 0xe3686e0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+ [stage(a, placeholder(a, 0x22c264a0)), stage(b, placeholder(b, 0x5bde450)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 4974978066..4fde9ca036 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**14:39.169** total execution time for **tutorial** files:
+**14:17.749** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:08.730 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:24.491 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:25.906 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:35.299 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.358 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.276 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:37.962 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:41.458 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:22.915 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.428 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.307 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.817 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.816 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.790 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.179 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 3d694d7b1a..42a56ce03a 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -295,7 +295,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000008
- naive: 0.000008
+ naive: 0.000007
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000009
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.69521000165696e-06 1.0
- naive 8.1393e-06 1.0577099258171534
- parallel 8.1727e-06 1.0620502881974925
- vector 2.45548e-05 3.190920065172071
+ numpy 7.64272001106292e-06 1.0
+ naive 6.6855e-06 0.8747540130114234
+ parallel 8.909300000000001e-06 1.1657237197102202
+ vector 2.45727e-05 3.2151773144156466
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018264
+ Numpy running time: 0.018447
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.453191
+ none: 3.197408
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.294637
+ blocking: 0.297889
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.331969
+ vectorization: 0.335439
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.117642
+ loop permutation: 0.116555
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109222
+ array packing: 0.108118
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110735
+ block caching: 0.109582
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145618
+ parallelization: 0.145101
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4531908412999996 1.0
- blocking 0.2946366399 0.08532301093126962
- vectorization 0.3319694918 0.0961341284210709
- loop permutation 0.1176423127 0.034067712474214716
- array packing 0.1092217145 0.03162921469433819
- block caching 0.11073531519999999 0.03206753414135438
- parallelization 0.1456179252 0.04216909284549712
+ none 3.1974078570000004 1.0
+ blocking 0.2978892441 0.09316585728900333
+ vectorization 0.3354392912 0.10490976009383089
+ loop permutation 0.1165554261 0.03645309929567737
+ array packing 0.1081175454 0.03381412388891868
+ block caching 0.109581649 0.034272027186051914
+ parallelization 0.1451011303 0.04538086374634188
@@ -1661,11 +1661,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.358 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index dd1cb448bd..16d2ceef5f 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-f8691180e044545bbd9582dfbc3d363e454029ad
+b807613c794321bf4fa765df026b1c3b454811b3
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 3bb8aceb78..a6ec5391a3 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> ( 2 minutes 26.741 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.319 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 058cda888a..c6e86b1fac 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 965ms/step
+1/1 [==============================] - 1s 959ms/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 d521c5d0d3..26eb97fd48 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipbdb840dc-a02e-459b-b71d-cb7f50bcce26 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.zipdfe62a7a-981d-4de5-9f39-5cf27e7656f3 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 bd6374cc8b..85be6eff93 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,16 +448,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 40.1MB/s]
- 24%|##4 | 10.2M/41.5M [00:00<00:00, 35.5MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 34.6MB/s]
- 42%|####2 | 17.6M/41.5M [00:00<00:00, 31.4MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 34.1MB/s]
- 62%|######1 | 25.6M/41.5M [00:00<00:00, 32.3MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.7MB/s]
- 90%|########9 | 37.2M/41.5M [00:01<00:00, 36.6MB/s]
- 99%|#########9| 41.2M/41.5M [00:01<00:00, 38.0MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 36.2MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 45.7MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 53.2MB/s]
+ 47%|####7 | 19.6M/41.5M [00:00<00:00, 48.4MB/s]
+ 59%|#####8 | 24.3M/41.5M [00:00<00:00, 43.9MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 48.8MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 41.0MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 44.7MB/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 e3140bb665..4191a7363a 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,10 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 12%|#1 | 5.18M/44.7M [00:00<00:00, 46.2MB/s]
- 54%|#####3 | 24.0M/44.7M [00:00<00:00, 126MB/s]
- 81%|########1 | 36.4M/44.7M [00:00<00:00, 115MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 108MB/s]
+ 27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
+ 55%|#####4 | 24.5M/44.7M [00:00<00:00, 108MB/s]
+ 78%|#######8 | 34.9M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 50928128fb..fdc53f0a6a 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.490 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.048 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 d039a6f8f7..7c5b0988b8 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:11.205</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:55.117</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -348,44 +348,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>02:26.741</p></td>
+<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>01:15.048</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:14.490</p></td>
+<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>01:14.319</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>00:47.272</p></td>
+<td><p>00:47.494</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:32.770</p></td>
+<td><p>00:33.489</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>00:32.392</p></td>
+<td><p>00:30.793</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>00:28.414</p></td>
+<td><p>00:27.199</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.854</p></td>
+<td><p>00:24.517</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>00:23.370</p></td>
+<td><p>00:22.481</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:18.399</p></td>
+<td><p>00:17.375</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>00:02.502</p></td>
+<td><p>00:02.402</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index b0c13c5c95..27bd96f459 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)
- 15.7911 15.8094 15.9672 15.6082 0.1131
+ 17.0029 16.8330 19.0178 15.9217 0.9652
</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 9abdaf29b1..ccb4c4d3f1 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,21 +453,22 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 4%|3 | 6.30M/170M [00:00<00:02, 63.8MB/s]
- 9%|9 | 16.0M/170M [00:00<00:01, 83.1MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:01, 108MB/s]
- 28%|##8 | 48.0M/170M [00:00<00:01, 125MB/s]
- 35%|###5 | 59.8M/170M [00:00<00:01, 104MB/s]
- 41%|####1 | 70.1M/170M [00:00<00:01, 97.0MB/s]
- 47%|####6 | 79.5M/170M [00:00<00:00, 95.2MB/s]
- 52%|#####2 | 88.7M/170M [00:01<00:01, 75.2MB/s]
- 59%|#####9 | 101M/170M [00:01<00:00, 88.0MB/s]
- 66%|######5 | 112M/170M [00:01<00:00, 91.5MB/s]
- 74%|#######4 | 126M/170M [00:01<00:00, 103MB/s]
- 80%|######## | 137M/170M [00:01<00:00, 85.6MB/s]
- 86%|########5 | 145M/170M [00:01<00:00, 74.9MB/s]
- 99%|#########8| 168M/170M [00:01<00:00, 111MB/s]
-100%|##########| 170M/170M [00:01<00:00, 96.2MB/s]
+ 7%|6 | 11.6M/170M [00:00<00:01, 122MB/s]
+ 14%|#3 | 23.2M/170M [00:00<00:01, 121MB/s]
+ 20%|## | 34.8M/170M [00:00<00:01, 101MB/s]
+ 27%|##7 | 46.7M/170M [00:00<00:01, 109MB/s]
+ 34%|###3 | 57.4M/170M [00:00<00:01, 103MB/s]
+ 40%|###9 | 67.4M/170M [00:00<00:01, 102MB/s]
+ 46%|####5 | 77.7M/170M [00:00<00:00, 104MB/s]
+ 52%|#####1 | 87.7M/170M [00:00<00:00, 103MB/s]
+ 57%|#####7 | 97.6M/170M [00:01<00:00, 90.5MB/s]
+ 65%|######5 | 111M/170M [00:01<00:00, 105MB/s]
+ 72%|#######1 | 122M/170M [00:01<00:00, 99.3MB/s]
+ 77%|#######7 | 131M/170M [00:01<00:00, 101MB/s]
+ 84%|########3 | 142M/170M [00:01<00:00, 103MB/s]
+ 90%|########9 | 152M/170M [00:01<00:00, 96.2MB/s]
+ 95%|#########5| 162M/170M [00:01<00:00, 88.9MB/s]
+100%|##########| 170M/170M [00:01<00:00, 101MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -565,7 +566,7 @@ 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 10.296 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 13.009 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 852f7e18ef..1dd1140b63 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,9 +497,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 42.8MB/s]
- 90%|########9 | 12.2M/13.6M [00:00<00:00, 33.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 37.7MB/s]
+ 60%|#####9 | 8.12M/13.6M [00:00<00:00, 84.8MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 104MB/s]
</pre></div>
</div>
</div>
@@ -590,7 +589,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.1637 90.0786 91.2555 89.9017 0.2564
+ 90.3124 90.2312 92.6501 90.0818 0.2875
</pre></div>
</div>
<div class="admonition note">
@@ -629,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.283 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.208 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 dc181d003e..f443070d0a 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.9897 118.8924 125.5482 117.7585 0.8257
+ 121.2563 121.2194 122.6003 120.3327 0.3435
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.966 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 24.948 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 445e0b156d..43e42ab00b 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 35.435 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.179 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 5856ab5b16..585403c245 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,26 +462,24 @@ 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]
- 2%|2 | 3296/132723 [00:00<00:06, 21215.21KB/s]
- 7%|7 | 9462/132723 [00:00<00:03, 40588.16KB/s]
- 12%|#1 | 15680/132723 [00:00<00:02, 42092.50KB/s]
- 15%|#5 | 20118/132723 [00:00<00:03, 34298.50KB/s]
- 21%|##1 | 27985/132723 [00:00<00:02, 46482.88KB/s]
- 26%|##6 | 34630/132723 [00:00<00:01, 52107.97KB/s]
- 32%|###2 | 42510/132723 [00:00<00:01, 59767.24KB/s]
- 37%|###7 | 49140/132723 [00:01<00:01, 52715.75KB/s]
- 43%|####2 | 56617/132723 [00:01<00:01, 58492.29KB/s]
- 48%|####8 | 64310/132723 [00:01<00:01, 60902.87KB/s]
- 53%|#####3 | 70685/132723 [00:01<00:01, 56202.94KB/s]
- 59%|#####9 | 78731/132723 [00:01<00:00, 62539.33KB/s]
- 64%|######4 | 85256/132723 [00:01<00:00, 53806.36KB/s]
- 70%|####### | 93182/132723 [00:01<00:00, 60122.63KB/s]
- 75%|#######5 | 99588/132723 [00:01<00:00, 46841.54KB/s]
- 81%|######## | 107505/132723 [00:02<00:00, 54037.64KB/s]
- 86%|########6 | 114654/132723 [00:02<00:00, 58247.57KB/s]
- 91%|#########1| 121093/132723 [00:02<00:00, 47438.23KB/s]
- 97%|#########7| 129116/132723 [00:02<00:00, 54817.26KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 52843.12KB/s]
+ 4%|3 | 5259/132723 [00:00<00:02, 52583.78KB/s]
+ 10%|9 | 12778/132723 [00:00<00:01, 65872.72KB/s]
+ 15%|#5 | 20561/132723 [00:00<00:01, 71329.31KB/s]
+ 22%|##1 | 28557/132723 [00:00<00:01, 74734.53KB/s]
+ 27%|##7 | 36479/132723 [00:00<00:01, 76350.57KB/s]
+ 33%|###3 | 44339/132723 [00:00<00:01, 77113.67KB/s]
+ 39%|###9 | 52283/132723 [00:00<00:01, 77867.27KB/s]
+ 45%|####5 | 60213/132723 [00:00<00:00, 78318.01KB/s]
+ 51%|#####1 | 68115/132723 [00:00<00:00, 78533.72KB/s]
+ 57%|#####7 | 75987/132723 [00:01<00:00, 78589.28KB/s]
+ 63%|######3 | 83883/132723 [00:01<00:00, 78700.80KB/s]
+ 69%|######9 | 91781/132723 [00:01<00:00, 78784.26KB/s]
+ 75%|#######5 | 99660/132723 [00:01<00:00, 78763.56KB/s]
+ 81%|########1 | 107537/132723 [00:01<00:00, 78077.76KB/s]
+ 87%|########6 | 115347/132723 [00:01<00:00, 77481.75KB/s]
+ 93%|#########2| 123101/132723 [00:01<00:00, 77497.21KB/s]
+ 99%|#########8| 131035/132723 [00:01<00:00, 78038.43KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 76850.12KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -520,7 +518,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 59.141 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 1.623 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 3cf51de9a4..bcbe9c8366 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>12:36.200</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:38.418</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:10.296</p></td>
+<td><p>03:13.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:59.141</p></td>
+<td><p>03:01.623</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>02:20.966</p></td>
+<td><p>02:24.948</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>01:35.435</p></td>
+<td><p>01:25.179</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:05.283</p></td>
+<td><p>01:07.208</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:35.759</p></td>
+<td><p>00:36.920</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:24.916</p></td>
+<td><p>00:25.033</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.397</p></td>
+<td><p>00:24.491</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
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 bc5becacc9..2f47641678 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip5c654c38-96ec-4c46-a8a9-7b73df95dd6a 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.zip76f61c28-5c50-4565-9f8f-60f0d9db841f 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 4047281e3c..e079ac605b 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>00:49.782</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.505</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:46.325</p></td>
+<td><p>00:43.072</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>00:02.393</p></td>
+<td><p>00:02.401</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>00:01.057</p></td>
+<td><p>00:01.024</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 2c15f68aa1..c88c48efa7 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6665us [6665us] (46.51%; 46.51%)
-FoldScaleAxis: 7667us [6us] (53.49%; 53.49%)
- FoldConstant: 7661us [1523us] (53.45%; 99.93%)
- InferType: 6138us [6138us] (42.83%; 80.12%)
+InferType: 7241us [7241us] (47.69%; 47.69%)
+FoldScaleAxis: 7941us [6us] (52.31%; 52.31%)
+ FoldConstant: 7935us [1632us] (52.27%; 99.93%)
+ InferType: 6303us [6303us] (41.51%; 79.43%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6160us [6160us] (44.74%; 44.74%)
-FoldScaleAxis: 7609us [5us] (55.26%; 55.26%)
- FoldConstant: 7604us [1535us] (55.23%; 99.94%)
- InferType: 6069us [6069us] (44.08%; 79.81%)
+InferType: 6366us [6366us] (44.64%; 44.64%)
+FoldScaleAxis: 7895us [5us] (55.36%; 55.36%)
+ FoldConstant: 7890us [1648us] (55.33%; 99.94%)
+ InferType: 6242us [6242us] (43.77%; 79.11%)
</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 100ba9f7b4..cfc2e4d956 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.154079 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 39.971710 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 d657a9a1a7..f4960dad37 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -916,7 +916,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.472153 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.361130 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 8f11fa1d58..56ebeb6188 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018238
-Baseline: 3.440224
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018666
+Baseline: 3.201057
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -535,7 +535,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300349
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.293776
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -602,7 +602,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335285
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.339217
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -663,7 +663,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116285
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117332
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -746,7 +746,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108824
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109443
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -832,7 +832,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111131
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -922,7 +922,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147327
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148696
</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 ef09ca7dbc..06d281688a 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.010</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.436</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.352</p></td>
+<td><p>00:31.745</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>00:01.515</p></td>
+<td><p>00:01.538</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>00:01.143</p></td>
+<td><p>00:01.152</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 6ebf6e79ba..614dbff1ae 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>09:49.553</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:11.042</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>06:17.110</p></td>
+<td><p>05:39.665</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:33.564</p></td>
+<td><p>01:34.085</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>01:05.348</p></td>
+<td><p>01:04.288</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>00:30.640</p></td>
+<td><p>00:29.315</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:11.831</p></td>
+<td><p>00:12.228</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.059</p></td>
+<td><p>00:11.461</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 d291b7dc16..46c1ab6ef1 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
@@ -488,9 +488,6 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
-</pre></div>
-</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -507,12 +504,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [28], [], scope="local")[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -526,463 +523,421 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((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)]))
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_1: int32 = (rc.outer.outer*36)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[(threadIdx.x_1*3)] = @tir.if_then_else((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (0 < floormod(threadIdx.x_1, 3))), data[(((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)), data[(((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (floormod(threadIdx.x_1, 3) < 2)), data[(((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 52), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 168)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 2), 27)) && (floormod((threadIdx.x_1 + 2), 27) < 24)) && (1 < floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 169)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 2), 27)) && (floormod((threadIdx.x_1 + 2), 27) < 24)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 170)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 2), 27)) && (floormod((threadIdx.x_1 + 2), 27) < 24)) && (1 < floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (ry.outer.inner*3)) + 137)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ for (i2.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
}
}
}
@@ -1020,7 +975,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.363 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.304 ms
</pre></div>
</div>
</div>
@@ -1050,35 +1005,35 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=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_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=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=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)
@@ -1098,12 +1053,12 @@ 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=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=3)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1123,10 +1078,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[28];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1141,411 +1096,396 @@ 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) {
- __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);
- }
- 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);
- }
- 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)]));
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 3)] = ((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = ((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 52) {
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 168)] = (((((3 <= ((((int)threadIdx.x) + 2) % 27)) && (((((int)threadIdx.x) + 2) % 27) < 24)) && (1 < (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 169)] = (((((3 <= ((((int)threadIdx.x) + 2) % 27)) && (((((int)threadIdx.x) + 2) % 27) < 24)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 170)] = (((((3 <= ((((int)threadIdx.x) + 2) % 27)) && (((((int)threadIdx.x) + 2) % 27) < 24)) && (1 < (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (ry_outer_inner * 3)) + 137)]));
}
}
- 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 < 4; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1583,7 +1523,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 17.110 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 39.665 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 2a9d6060f0..e3e469ca97 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2274 8.2274 8.2385 8.2162 0.0091
+ 8.2366 8.2315 8.2469 8.2313 0.0073
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.348 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.288 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 a070efe2a2..61d4690b1b 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 753.7040 754.1751 754.5343 752.4026 0.9319
+ 754.6781 753.9550 756.2006 753.8788 1.0770
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.564 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.085 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 47696866ae..0387325372 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,78 +632,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
+ for (i.outer.inner: int32, 0, 8) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 64) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -741,7 +695,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.866 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.518 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 cf7c59c593..90dc973be1 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>00:25.299</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:26.758</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:25.263</p></td>
+<td><p>00:26.723</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
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 f676677bb3..e054b0b1bf 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 63.15/63.15 result: MeasureResult(costs=(0.003665625142857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8789360523223877, timestamp=1667871847.9924874) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2915996
-No: 2 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -690,8 +689,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2790347
-No: 3 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,930047
+No: 2 GFLOPS: 12.05/12.05 result: MeasureResult(costs=(0.019211337999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.786815881729126, timestamp=1667929579.0447943) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,640704
+No: 3 GFLOPS: 0.00/12.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -813,8 +813,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9309823
-No: 4 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7699149
+No: 4 GFLOPS: 35.32/35.32 result: MeasureResult(costs=(0.0065546979375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.174964427947998, timestamp=1667929580.6686113) [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('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', 512), ('unroll_explicit', 1)],None,8523364
+No: 5 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -936,8 +937,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10365241
-No: 5 GFLOPS: 0.00/63.15 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, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2680243
+No: 6 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1059,8 +1060,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,611541
-No: 6 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9798808
+No: 7 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1182,8 +1183,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8902723
-No: 7 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,331574
+No: 8 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1305,8 +1306,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5962142
-No: 8 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1373334
+No: 9 GFLOPS: 0.00/35.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1428,8 +1429,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3217062
-No: 9 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4883939
+No: 10 GFLOPS: 80.29/80.29 result: MeasureResult(costs=(0.002883404388888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9578070640563965, timestamp=1667929585.974) [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7269055
+No: 11 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1551,8 +1553,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10245233
-No: 10 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,308398
+No: 12 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1674,8 +1676,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9666364
-No: 11 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5932193
+No: 13 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1797,8 +1799,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10022506
-No: 12 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6763803
+No: 14 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1920,8 +1922,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1531370
-No: 13 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5586598
+No: 15 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2043,8 +2045,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6747722
-No: 14 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8335410
+No: 16 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2166,9 +2168,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4113806
-No: 15 GFLOPS: 6.84/63.15 result: MeasureResult(costs=(0.03384215925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7952816486358643, timestamp=1667871854.1375206) [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2612672
-No: 16 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2182952
+No: 17 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2290,8 +2291,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8967516
-No: 17 GFLOPS: 0.00/63.15 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, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9855387
+No: 18 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2413,8 +2414,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2836766
-No: 18 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1970282
+No: 19 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2536,9 +2537,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4434408
-No: 19 GFLOPS: 36.41/63.15 result: MeasureResult(costs=(0.006358260125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2706403732299805, timestamp=1667871855.6317317) [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6919947
-No: 20 GFLOPS: 0.00/63.15 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4287496
+No: 20 GFLOPS: 0.00/80.29 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2660,7 +2660,7 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9590006
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8314704
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2699,9 +2699,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2915996
+[('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7269055
Finish loading 20 records
-Time cost of this operator: 0.001870
+Time cost of this operator: 0.001537
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index ed5f185353..b6ef73f80c 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -595,10 +595,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.9 98.752 (1, 2, 10, 10, 3) 2 1 [316.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.941 (1, 6, 10, 10) 1 1 [3.021]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.307 (1, 1, 10, 10, 3) 1 1 [0.984]
-Total_time - 320.905 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.4 98.713 (1, 2, 10, 10, 3) 2 1 [312.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.085 0.975 (1, 6, 10, 10) 1 1 [3.085]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.989 0.313 (1, 1, 10, 10, 3) 1 1 [0.989]
+Total_time - 316.474 - - - - -
</pre></div>
</div>
</div>
@@ -649,10 +649,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.4 97.516 (1, 6, 10, 10, 1) 2 1 [103.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.792 1.69 (1, 6, 10, 10) 1 1 [1.792]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.794 (1, 3, 10, 10, 1) 1 1 [0.842]
-Total_time - 106.034 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.5 97.925 (1, 6, 10, 10, 1) 2 1 [134.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.877 1.366 (1, 6, 10, 10) 1 1 [1.877]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.709 (1, 1, 10, 10, 3) 1 1 [0.974]
+Total_time - 137.35 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index c4026adedb..0a8c309915 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -529,7 +529,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp2liubq2r/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp_ifu4zvj/images/random'
</pre></div>
</div>
</div>
@@ -589,8 +589,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [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/tmp2liubq2r/images/target contains 8144 images
-/tmp/tmp2liubq2r/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp_ifu4zvj/images/target contains 8144 images
+/tmp/tmp_ifu4zvj/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -702,13 +702,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2407 - accuracy: 0.9184 - val_loss: 0.1110 - val_accuracy: 0.9626 - 47s/epoch - 143ms/step
+328/328 - 46s - loss: 0.2264 - accuracy: 0.9224 - val_loss: 0.2056 - val_accuracy: 0.9282 - 46s/epoch - 142ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.1017 - accuracy: 0.9624 - val_loss: 0.0952 - val_accuracy: 0.9660 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.1044 - accuracy: 0.9598 - val_loss: 0.0932 - val_accuracy: 0.9690 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0678 - accuracy: 0.9735 - val_loss: 0.2055 - val_accuracy: 0.9279 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0682 - accuracy: 0.9746 - val_loss: 0.0979 - val_accuracy: 0.9679 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7efd751fb490>
+<keras.callbacks.History object at 0x7fe5f02e7f10>
</pre></div>
</div>
</div>
@@ -970,7 +970,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 32.531 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 19.422 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 ccde41d0b7..d0964399c7 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:33.660</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:21.859</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:32.531</p></td>
+<td><p>04:19.422</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:49.569</p></td>
+<td><p>00:49.988</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.837</p></td>
+<td><p>00:08.655</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.721</p></td>
+<td><p>00:03.792</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 99fbc177b0..65da068ebf 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.899</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.995</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>00:32.221</p></td>
+<td><p>00:31.900</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>00:10.089</p></td>
+<td><p>00:10.313</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>00:01.581</p></td>
+<td><p>00:01.775</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 2076c6e004..ea3d76ecd8 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 0x7efdce4144d0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fe5929f2830>
</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 7caa2c9ecf..4d8588f0f2 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:06.481</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.910</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,31 +349,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.153</p></td>
+<td><p>00:02.387</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>00:00.993</p></td>
+<td><p>00:01.169</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>00:00.570</p></td>
+<td><p>00:00.577</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>00:00.545</p></td>
+<td><p>00:00.566</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>00:00.120</p></td>
+<td><p>00:00.114</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>00:00.054</p></td>
+<td><p>00:00.049</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 5743d61cfb..20bc6863af 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -590,7 +590,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpxpc6rtyo/input0.cc'\nsource_filename = \"/tmp/tmpxpc6rtyo/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpisxaqdoi/input0.cc'\nsource_filename = \"/tmp/tmpisxaqdoi/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 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 e27fde871e..a344cdef74 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 476ba90f5a..8d30ee73f9 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/f8691180e/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index a877828833..7c13cfd679 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/f8691180e/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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 77f88dfe1c..a12c10de8f 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/f8691180e/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 4c2cbb6891..f542b6b00d 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/f8691180e/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 3ead33fe0f..7319b7864c 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/f8691180e/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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 c38fc7f8d3..6212b608e5 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/f8691180e/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 75946f33ee..ec5f6aa8f0 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 9a78f9d5c4..19fd03183c 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index ec20f38d13..34ec863883 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/f8691180e/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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 d9f4c32a49..d006d4a8a6 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index ff30543f27..847182897a 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/f8691180e/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index aefae0e8b1..bf774f9479 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index d5e2dcbb20..c067dffe39 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/f8691180e/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index adde3296f5..70253b5fba 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/f8691180e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index a3f78ee228..f9f9eedcb4 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/f8691180e/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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 3d8a1638b7..54a71911eb 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/f8691180e/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index ded9d9231b..7c30300fb0 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/f8691180e/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 974068f0a2..f00864df90 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/f8691180e/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index f71a671ec9..3d52fc1771 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/f8691180e/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 755e727cdd..3b361b38b1 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/f8691180e/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index c3fac492a2..bb134f9eab 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index dd5b70a4ac..edb6f9c72d 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/f8691180e/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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 4f93737c40..23b182442c 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/f8691180e/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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 096c61b0a4..a79fbc0f3d 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/f8691180e/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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/f8691180e/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b807613c7/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 5dbf53ebee..5a40cc7cf1 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 efa82a2642..44968ed290 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:26.921</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.740</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:26.915</p></td>
+<td><p>00:26.734</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index c786c498f6..155c1286c8 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 31.21s!
+resnet18_v1 inference graph built in 28.67s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index b2518e7e06..834514a4bf 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 20.85s!
+yolov3-tiny inference graph built in 19.46s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 11821d18bb..77439bcf35 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:44.499</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:40.427</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:53.275</p></td>
+<td><p>00:51.776</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:51.224</p></td>
+<td><p>00:48.651</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 7e6bf87867..5020c3713b 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.423</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.090</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.969</p></td>
+<td><p>00:02.634</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.455</p></td>
+<td><p>00:00.456</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 8ffcf0dbf8..87cbf652c6 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.791</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.812</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.422</p></td>
+<td><p>00:00.436</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.370</p></td>
+<td><p>00:00.376</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 3d39ef6d0b..6045de7f8a 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,6 +491,9 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
+</pre></div>
+</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -578,7 +581,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.971 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.445 ms
</pre></div>
</div>
</div>
@@ -652,7 +655,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.906 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 35.299 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index f127c98d13..f0eefc1fb1 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 1.76/1.76 result: MeasureResult(costs=(0.15216853219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.588067054748535, timestamp=1667870407.7993975) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
-No: 2 GFLOPS: 4.30/4.30 result: MeasureResult(costs=(0.0624862162,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2039549350738525, timestamp=1667870409.003014) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
-No: 3 GFLOPS: 10.81/10.81 result: MeasureResult(costs=(0.0248387668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5392439365386963, timestamp=1667870410.3107543) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
-No: 4 GFLOPS: 9.47/10.81 result: MeasureResult(costs=(0.0283396608,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6711032390594482, timestamp=1667870411.660674) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
-No: 5 GFLOPS: 2.75/10.81 result: MeasureResult(costs=(0.0977128568,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7126760482788086, timestamp=1667870413.5966527) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
-No: 6 GFLOPS: 3.01/10.81 result: MeasureResult(costs=(0.08909641,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.587338924407959, timestamp=1667870415.1883016) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
-No: 7 GFLOPS: 0.94/10.81 result: MeasureResult(costs=(0.2842348806,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.706167459487915, timestamp=1667870420.6292396) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
-No: 8 GFLOPS: 9.66/10.81 result: MeasureResult(costs=(0.027790581800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7444319725036621, timestamp=1667870421.2817755) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
-No: 9 GFLOPS: 2.40/10.81 result: MeasureResult(costs=(0.1120682792,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9104909896850586, timestamp=1667870423.527031) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
-No: 10 GFLOPS: 9.15/10.81 result: MeasureResult(costs=(0.029330837600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8099238872528076, timestamp=1667870424.164117) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+No: 1 GFLOPS: 0.49/0.49 result: MeasureResult(costs=(0.5436071125999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.832136392593384, timestamp=1667928192.2193973) [('tile_y', [-1, 512]), ('tile_x', [-1, 1])],None,9
+No: 2 GFLOPS: 0.51/0.51 result: MeasureResult(costs=(0.5277764916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.560190200805664, timestamp=1667928201.5797062) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
+No: 3 GFLOPS: 13.84/13.84 result: MeasureResult(costs=(0.0193974372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.496504545211792, timestamp=1667928202.7938218) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+No: 4 GFLOPS: 1.52/13.84 result: MeasureResult(costs=(0.176035852,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.965695381164551, timestamp=1667928206.525283) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+No: 5 GFLOPS: 0.51/13.84 result: MeasureResult(costs=(0.527366442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.58648157119751, timestamp=1667928215.2718334) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+No: 6 GFLOPS: 10.77/13.84 result: MeasureResult(costs=(0.024925931800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5907962322235107, timestamp=1667928215.8398972) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
+No: 7 GFLOPS: 1.77/13.84 result: MeasureResult(costs=(0.1518953626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.578155755996704, timestamp=1667928218.4322212) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+No: 8 GFLOPS: 3.71/13.84 result: MeasureResult(costs=(0.0724365372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3622841835021973, timestamp=1667928219.8061028) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+No: 9 GFLOPS: 13.56/13.84 result: MeasureResult(costs=(0.019802845,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.43721771240234375, timestamp=1667928220.3544896) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
+No: 10 GFLOPS: 10.01/13.84 result: MeasureResult(costs=(0.0268292798,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5377368927001953, timestamp=1667928220.9470682) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 6baaae3025..0aa784d4cd 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 510.6892897400006, 'median': 510.96751540000014, 'std': 1.8923402940276843}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 513.2742928301741, 'median': 513.4689666498161, 'std': 1.5081723780732224}
</pre></div>
</div>
</div>
@@ -712,179 +712,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 23.93/ 23.93 GFLOPS | Progress: (4/20) | 7.63 s
-[Task 1/25] Current/Best: 9.46/ 23.93 GFLOPS | Progress: (8/20) | 11.28 s
-[Task 1/25] Current/Best: 19.36/ 23.93 GFLOPS | Progress: (12/20) | 12.85 s
-[Task 1/25] Current/Best: 14.74/ 23.93 GFLOPS | Progress: (16/20) | 18.71 s
-[Task 1/25] Current/Best: 23.15/ 23.93 GFLOPS | Progress: (20/20) | 20.80 s Done.
+[Task 1/25] Current/Best: 15.09/ 18.83 GFLOPS | Progress: (4/20) | 6.67 s
+[Task 1/25] Current/Best: 17.07/ 18.83 GFLOPS | Progress: (8/20) | 11.12 s
+[Task 1/25] Current/Best: 14.52/ 19.01 GFLOPS | Progress: (12/20) | 14.01 s
+[Task 1/25] Current/Best: 22.82/ 22.82 GFLOPS | Progress: (16/20) | 16.12 s
+[Task 1/25] Current/Best: 17.60/ 23.41 GFLOPS | Progress: (20/20) | 17.82 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.00/ 18.92 GFLOPS | Progress: (4/20) | 3.00 s
-[Task 2/25] Current/Best: 14.06/ 18.92 GFLOPS | Progress: (8/20) | 4.63 s
-[Task 2/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (12/20) | 6.23 s
-[Task 2/25] Current/Best: 9.02/ 20.08 GFLOPS | Progress: (16/20) | 7.90 s
-[Task 2/25] Current/Best: 17.88/ 20.08 GFLOPS | Progress: (20/20) | 9.54 s Done.
+[Task 2/25] Current/Best: 5.56/ 14.23 GFLOPS | Progress: (4/20) | 3.17 s
+[Task 2/25] Current/Best: 5.69/ 19.71 GFLOPS | Progress: (8/20) | 4.51 s
+[Task 2/25] Current/Best: 3.20/ 20.62 GFLOPS | Progress: (12/20) | 5.88 s
+[Task 2/25] Current/Best: 5.09/ 20.62 GFLOPS | Progress: (16/20) | 7.19 s
+[Task 2/25] Current/Best: 11.91/ 20.62 GFLOPS | Progress: (20/20) | 8.52 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 19.53/ 19.53 GFLOPS | Progress: (4/20) | 3.88 s
-[Task 3/25] Current/Best: 8.21/ 19.53 GFLOPS | Progress: (8/20) | 7.81 s
-[Task 3/25] Current/Best: 9.44/ 19.53 GFLOPS | Progress: (12/20) | 10.41 s
-[Task 3/25] Current/Best: 8.11/ 19.53 GFLOPS | Progress: (16/20) | 12.72 s
-[Task 3/25] Current/Best: 16.55/ 19.53 GFLOPS | Progress: (20/20) | 15.85 s Done.
+[Task 3/25] Current/Best: 3.12/ 18.57 GFLOPS | Progress: (4/20) | 4.14 s
+[Task 3/25] Current/Best: 7.09/ 18.57 GFLOPS | Progress: (8/20) | 6.29 s
+[Task 3/25] Current/Best: 8.40/ 18.57 GFLOPS | Progress: (12/20) | 10.17 s
+[Task 3/25] Current/Best: 15.91/ 18.57 GFLOPS | Progress: (16/20) | 13.97 s
+[Task 3/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (20/20) | 16.06 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (4/20) | 7.74 s
-[Task 4/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (8/20) | 9.73 s
-[Task 4/25] Current/Best: 14.55/ 23.06 GFLOPS | Progress: (12/20) | 12.00 s
-[Task 4/25] Current/Best: 4.78/ 23.06 GFLOPS | Progress: (16/20) | 13.82 s
-[Task 4/25] Current/Best: 13.19/ 23.06 GFLOPS | Progress: (20/20) | 16.07 s Done.
+[Task 4/25] Current/Best: 12.56/ 12.56 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 4/25] Current/Best: 13.11/ 13.11 GFLOPS | Progress: (8/20) | 6.08 s
+[Task 4/25] Current/Best: 6.66/ 13.67 GFLOPS | Progress: (12/20) | 8.55 s
+[Task 4/25] Current/Best: 15.60/ 15.60 GFLOPS | Progress: (16/20) | 10.32 s
+[Task 4/25] Current/Best: 13.58/ 16.93 GFLOPS | Progress: (20/20) | 12.81 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 14.50/ 21.95 GFLOPS | Progress: (4/20) | 3.03 s
-[Task 5/25] Current/Best: 13.08/ 21.95 GFLOPS | Progress: (8/20) | 5.29 s
-[Task 5/25] Current/Best: 22.76/ 22.76 GFLOPS | Progress: (12/20) | 7.42 s
-[Task 5/25] Current/Best: 9.66/ 22.76 GFLOPS | Progress: (16/20) | 9.62 s
-[Task 5/25] Current/Best: 13.64/ 22.76 GFLOPS | Progress: (20/20) | 12.03 s Done.
+[Task 5/25] Current/Best: 11.27/ 22.82 GFLOPS | Progress: (4/20) | 3.22 s
+[Task 5/25] Current/Best: 4.92/ 22.82 GFLOPS | Progress: (8/20) | 4.83 s
+[Task 5/25] Current/Best: 16.53/ 22.82 GFLOPS | Progress: (12/20) | 6.81 s
+[Task 5/25] Current/Best: 5.56/ 22.82 GFLOPS | Progress: (16/20) | 8.54 s
+[Task 5/25] Current/Best: 3.08/ 22.82 GFLOPS | Progress: (20/20) | 10.54 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 8.94/ 14.33 GFLOPS | Progress: (4/20) | 4.72 s
-[Task 6/25] Current/Best: 9.62/ 14.33 GFLOPS | Progress: (8/20) | 6.88 s
-[Task 6/25] Current/Best: 8.12/ 18.17 GFLOPS | Progress: (12/20) | 8.91 s
-[Task 6/25] Current/Best: 19.09/ 19.09 GFLOPS | Progress: (16/20) | 11.28 s
-[Task 6/25] Current/Best: 14.31/ 19.47 GFLOPS | Progress: (20/20) | 14.19 s Done.
+[Task 6/25] Current/Best: 11.72/ 15.23 GFLOPS | Progress: (4/20) | 3.87 s
+[Task 6/25] Current/Best: 4.99/ 15.23 GFLOPS | Progress: (8/20) | 6.26 s
+[Task 6/25] Current/Best: 10.08/ 15.23 GFLOPS | Progress: (12/20) | 8.52 s
+[Task 6/25] Current/Best: 10.25/ 19.91 GFLOPS | Progress: (16/20) | 10.13 s
+[Task 6/25] Current/Best: 3.07/ 19.91 GFLOPS | Progress: (20/20) | 13.17 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 6.04/ 15.97 GFLOPS | Progress: (4/20) | 3.55 s
-[Task 7/25] Current/Best: 12.56/ 19.71 GFLOPS | Progress: (8/20) | 5.38 s
-[Task 7/25] Current/Best: 5.04/ 19.71 GFLOPS | Progress: (12/20) | 7.47 s
-[Task 7/25] Current/Best: 15.12/ 19.71 GFLOPS | Progress: (16/20) | 9.65 s
-[Task 7/25] Current/Best: 16.83/ 19.71 GFLOPS | Progress: (20/20) | 11.26 s Done.
+[Task 7/25] Current/Best: 19.61/ 19.61 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 7/25] Current/Best: 4.82/ 19.61 GFLOPS | Progress: (8/20) | 6.21 s
+[Task 7/25] Current/Best: 11.98/ 19.61 GFLOPS | Progress: (12/20) | 7.99 s
+[Task 7/25] Current/Best: 8.34/ 20.09 GFLOPS | Progress: (16/20) | 9.91 s
+[Task 7/25] Current/Best: 15.21/ 20.09 GFLOPS | Progress: (20/20) | 12.40 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 13.95/ 13.95 GFLOPS | Progress: (4/20) | 4.46 s
-[Task 8/25] Current/Best: 11.13/ 13.95 GFLOPS | Progress: (8/20) | 16.00 s
-[Task 8/25] Current/Best: 10.05/ 17.10 GFLOPS | Progress: (12/20) | 18.09 s
-[Task 8/25] Current/Best: 7.29/ 17.10 GFLOPS | Progress: (16/20) | 21.59 s
-[Task 8/25] Current/Best: 9.94/ 17.10 GFLOPS | Progress: (20/20) | 28.64 s Done.
+[Task 8/25] Current/Best: 3.63/ 18.25 GFLOPS | Progress: (4/20) | 7.14 s
+[Task 8/25] Current/Best: 4.49/ 18.25 GFLOPS | Progress: (8/20) | 10.15 s
+[Task 8/25] Current/Best: 14.35/ 18.25 GFLOPS | Progress: (12/20) | 15.26 s
+[Task 8/25] Current/Best: 19.10/ 21.36 GFLOPS | Progress: (16/20) | 17.22 s
+[Task 8/25] Current/Best: 7.98/ 21.36 GFLOPS | Progress: (20/20) | 19.77 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 13.96/ 19.84 GFLOPS | Progress: (4/20) | 4.09 s
-[Task 9/25] Current/Best: 11.39/ 19.84 GFLOPS | Progress: (8/20) | 7.80 s
-[Task 9/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (12/20) | 12.62 s
-[Task 9/25] Current/Best: 7.67/ 20.69 GFLOPS | Progress: (16/20) | 15.47 s
-[Task 9/25] Current/Best: 19.67/ 20.69 GFLOPS | Progress: (20/20) | 26.36 s Done.
+[Task 9/25] Current/Best: 21.74/ 21.74 GFLOPS | Progress: (4/20) | 5.57 s
+[Task 9/25] Current/Best: 13.41/ 21.74 GFLOPS | Progress: (8/20) | 10.22 s
+[Task 9/25] Current/Best: 6.06/ 21.74 GFLOPS | Progress: (12/20) | 17.90 s
+[Task 9/25] Current/Best: 6.66/ 23.02 GFLOPS | Progress: (16/20) | 19.23 s
+[Task 9/25] Current/Best: 3.24/ 23.02 GFLOPS | Progress: (20/20) | 21.48 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 12.14/ 19.27 GFLOPS | Progress: (4/20) | 3.91 s
-[Task 10/25] Current/Best: 6.84/ 19.27 GFLOPS | Progress: (8/20) | 5.26 s
-[Task 10/25] Current/Best: 9.11/ 19.27 GFLOPS | Progress: (12/20) | 6.81 s
-[Task 10/25] Current/Best: 14.49/ 19.27 GFLOPS | Progress: (16/20) | 9.34 s
-[Task 10/25] Current/Best: 4.30/ 19.27 GFLOPS | Progress: (20/20) | 12.08 s Done.
+[Task 10/25] Current/Best: 14.56/ 19.02 GFLOPS | Progress: (4/20) | 3.14 s
+[Task 10/25] Current/Best: 12.95/ 19.02 GFLOPS | Progress: (8/20) | 5.98 s
+[Task 10/25] Current/Best: 16.21/ 19.02 GFLOPS | Progress: (12/20) | 8.44 s
+[Task 10/25] Current/Best: 15.29/ 19.02 GFLOPS | Progress: (16/20) | 10.45 s
+[Task 10/25] Current/Best: 19.50/ 19.50 GFLOPS | Progress: (20/20) | 12.50 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 9.41/ 11.43 GFLOPS | Progress: (4/20) | 4.27 s
-[Task 11/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (8/20) | 7.60 s
-[Task 11/25] Current/Best: 18.59/ 21.72 GFLOPS | Progress: (12/20) | 9.13 s
-[Task 11/25] Current/Best: 16.40/ 21.72 GFLOPS | Progress: (16/20) | 11.01 s
-[Task 11/25] Current/Best: 14.39/ 21.72 GFLOPS | Progress: (20/20) | 12.99 s Done.
+[Task 11/25] Current/Best: 22.78/ 22.78 GFLOPS | Progress: (4/20) | 3.54 s
+[Task 11/25] Current/Best: 19.01/ 22.78 GFLOPS | Progress: (8/20) | 5.76 s
+[Task 11/25] Current/Best: 19.73/ 22.78 GFLOPS | Progress: (12/20) | 7.87 s
+[Task 11/25] Current/Best: 21.83/ 22.78 GFLOPS | Progress: (16/20) | 10.67 s
+[Task 11/25] Current/Best: 7.14/ 22.78 GFLOPS | Progress: (20/20) | 13.07 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 18.17/ 18.17 GFLOPS | Progress: (4/20) | 5.27 s
-[Task 12/25] Current/Best: 9.73/ 20.25 GFLOPS | Progress: (8/20) | 8.81 s
-[Task 12/25] Current/Best: 5.50/ 20.25 GFLOPS | Progress: (12/20) | 10.94 s
-[Task 12/25] Current/Best: 9.66/ 20.25 GFLOPS | Progress: (16/20) | 13.67 s
-[Task 12/25] Current/Best: 20.42/ 20.42 GFLOPS | Progress: (20/20) | 21.98 s Done.
+[Task 12/25] Current/Best: 16.51/ 18.52 GFLOPS | Progress: (4/20) | 4.21 s
+[Task 12/25] Current/Best: 17.60/ 21.08 GFLOPS | Progress: (8/20) | 7.03 s
+[Task 12/25] Current/Best: 4.80/ 21.08 GFLOPS | Progress: (12/20) | 9.49 s
+[Task 12/25] Current/Best: 17.49/ 21.70 GFLOPS | Progress: (16/20) | 10.92 s
+[Task 12/25] Current/Best: 15.30/ 21.70 GFLOPS | Progress: (20/20) | 13.56 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 12.08/ 14.94 GFLOPS | Progress: (4/20) | 3.75 s
-[Task 13/25] Current/Best: 20.00/ 22.16 GFLOPS | Progress: (8/20) | 5.70 s
-[Task 13/25] Current/Best: 17.29/ 22.16 GFLOPS | Progress: (12/20) | 9.54 s
-[Task 13/25] Current/Best: 21.14/ 22.16 GFLOPS | Progress: (16/20) | 11.57 s
-[Task 13/25] Current/Best: 19.69/ 22.16 GFLOPS | Progress: (20/20) | 14.63 s Done.
+[Task 13/25] Current/Best: 17.50/ 17.50 GFLOPS | Progress: (4/20) | 5.00 s
+[Task 13/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (8/20) | 7.26 s
+[Task 13/25] Current/Best: 23.10/ 23.10 GFLOPS | Progress: (12/20) | 10.00 s
+[Task 13/25] Current/Best: 17.40/ 23.10 GFLOPS | Progress: (16/20) | 12.15 s
+[Task 13/25] Current/Best: 14.28/ 23.10 GFLOPS | Progress: (20/20) | 14.14 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 8.27/ 14.30 GFLOPS | Progress: (4/20) | 3.50 s
-[Task 14/25] Current/Best: 9.43/ 14.30 GFLOPS | Progress: (8/20) | 10.24 s
-[Task 14/25] Current/Best: 16.59/ 16.59 GFLOPS | Progress: (12/20) | 13.60 s
-[Task 14/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (16/20) | 16.99 s
-[Task 14/25] Current/Best: 11.65/ 20.62 GFLOPS | Progress: (20/20) | 20.89 s
+[Task 14/25] Current/Best: 17.39/ 17.39 GFLOPS | Progress: (4/20) | 3.23 s
+[Task 14/25] Current/Best: 2.38/ 17.39 GFLOPS | Progress: (8/20) | 7.17 s
+[Task 14/25] Current/Best: 10.99/ 17.39 GFLOPS | Progress: (12/20) | 12.40 s
+[Task 14/25] Current/Best: 12.49/ 17.39 GFLOPS | Progress: (16/20) | 14.26 s
+[Task 14/25] Current/Best: 4.98/ 17.39 GFLOPS | Progress: (20/20) | 17.12 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 3.11/ 21.02 GFLOPS | Progress: (4/20) | 4.68 s
-[Task 15/25] Current/Best: 14.60/ 21.02 GFLOPS | Progress: (8/20) | 6.07 s
-[Task 15/25] Current/Best: 15.98/ 21.02 GFLOPS | Progress: (12/20) | 7.24 s Done.
+[Task 15/25] Current/Best: 9.43/ 18.98 GFLOPS | Progress: (4/20) | 4.05 s
+[Task 15/25] Current/Best: 16.90/ 18.98 GFLOPS | Progress: (8/20) | 5.25 s
+[Task 15/25] Current/Best: 19.67/ 19.67 GFLOPS | Progress: (12/20) | 12.55 s
+[Task 15/25] Current/Best: 13.86/ 19.67 GFLOPS | Progress: (16/20) | 14.09 s Done.
-[Task 15/25] Current/Best: 18.48/ 21.02 GFLOPS | Progress: (16/20) | 9.34 s
-[Task 15/25] Current/Best: 12.30/ 21.02 GFLOPS | Progress: (20/20) | 11.83 s Done.
+[Task 15/25] Current/Best: 9.67/ 19.67 GFLOPS | Progress: (20/20) | 17.27 s Done.
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 19.25/ 19.25 GFLOPS | Progress: (4/20) | 3.50 s
-[Task 16/25] Current/Best: 17.49/ 19.96 GFLOPS | Progress: (8/20) | 4.99 s
-[Task 16/25] Current/Best: 17.25/ 19.96 GFLOPS | Progress: (12/20) | 6.90 s
-[Task 16/25] Current/Best: 5.67/ 19.96 GFLOPS | Progress: (16/20) | 8.98 s
-[Task 16/25] Current/Best: 4.13/ 19.96 GFLOPS | Progress: (20/20) | 10.65 s Done.
+[Task 16/25] Current/Best: 14.72/ 14.72 GFLOPS | Progress: (4/20) | 3.91 s
+[Task 16/25] Current/Best: 15.95/ 18.15 GFLOPS | Progress: (8/20) | 5.26 s
+[Task 16/25] Current/Best: 14.99/ 21.20 GFLOPS | Progress: (12/20) | 6.45 s
+[Task 16/25] Current/Best: 15.23/ 22.24 GFLOPS | Progress: (16/20) | 8.03 s
+[Task 16/25] Current/Best: 5.36/ 22.24 GFLOPS | Progress: (20/20) | 10.25 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 8.95/ 17.40 GFLOPS | Progress: (4/20) | 4.03 s
-[Task 17/25] Current/Best: 18.01/ 18.01 GFLOPS | Progress: (8/20) | 6.76 s
-[Task 17/25] Current/Best: 11.59/ 18.35 GFLOPS | Progress: (12/20) | 8.74 s
-[Task 17/25] Current/Best: 5.16/ 21.08 GFLOPS | Progress: (16/20) | 10.90 s
-[Task 17/25] Current/Best: 16.99/ 21.08 GFLOPS | Progress: (20/20) | 13.17 s Done.
+[Task 17/25] Current/Best: 19.13/ 22.85 GFLOPS | Progress: (4/20) | 4.06 s
+[Task 17/25] Current/Best: 21.28/ 22.85 GFLOPS | Progress: (8/20) | 6.16 s
+[Task 17/25] Current/Best: 12.10/ 22.85 GFLOPS | Progress: (12/20) | 8.10 s
+[Task 17/25] Current/Best: 11.89/ 22.85 GFLOPS | Progress: (16/20) | 10.15 s
+[Task 17/25] Current/Best: 3.09/ 22.85 GFLOPS | Progress: (20/20) | 12.75 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 10.30/ 17.68 GFLOPS | Progress: (4/20) | 6.99 s
-[Task 18/25] Current/Best: 4.33/ 17.68 GFLOPS | Progress: (8/20) | 10.82 s
-[Task 18/25] Current/Best: 8.79/ 17.68 GFLOPS | Progress: (12/20) | 17.83 s
-[Task 18/25] Current/Best: 9.59/ 19.31 GFLOPS | Progress: (16/20) | 21.34 s
-[Task 18/25] Current/Best: 7.78/ 19.34 GFLOPS | Progress: (20/20) | 25.77 s Done.
+[Task 18/25] Current/Best: 3.04/ 12.57 GFLOPS | Progress: (4/20) | 5.61 s
+[Task 18/25] Current/Best: 21.33/ 21.33 GFLOPS | Progress: (8/20) | 7.69 s
+[Task 18/25] Current/Best: 22.01/ 22.01 GFLOPS | Progress: (12/20) | 9.46 s
+[Task 18/25] Current/Best: 18.44/ 22.01 GFLOPS | Progress: (16/20) | 11.10 s
+[Task 18/25] Current/Best: 17.04/ 22.01 GFLOPS | Progress: (20/20) | 12.55 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 10.33/ 12.76 GFLOPS | Progress: (4/20) | 6.51 s
-[Task 19/25] Current/Best: 8.37/ 19.06 GFLOPS | Progress: (8/20) | 10.04 s
-[Task 19/25] Current/Best: 13.27/ 19.06 GFLOPS | Progress: (12/20) | 13.53 s
-[Task 19/25] Current/Best: 9.74/ 19.06 GFLOPS | Progress: (16/20) | 16.47 s
-[Task 19/25] Current/Best: 7.03/ 19.06 GFLOPS | Progress: (20/20) | 19.87 s Done.
+[Task 19/25] Current/Best: 10.68/ 18.72 GFLOPS | Progress: (4/20) | 3.85 s
+[Task 19/25] Current/Best: 11.34/ 18.72 GFLOPS | Progress: (8/20) | 10.38 s
+[Task 19/25] Current/Best: 12.40/ 19.31 GFLOPS | Progress: (12/20) | 12.28 s
+[Task 19/25] Current/Best: 11.24/ 19.31 GFLOPS | Progress: (16/20) | 17.31 s
+[Task 19/25] Current/Best: 6.51/ 19.31 GFLOPS | Progress: (20/20) | 19.78 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 4.52/ 17.02 GFLOPS | Progress: (4/20) | 3.55 s
-[Task 20/25] Current/Best: 4.99/ 19.55 GFLOPS | Progress: (8/20) | 5.41 s
-[Task 20/25] Current/Best: 5.14/ 19.55 GFLOPS | Progress: (12/20) | 9.62 s
-[Task 20/25] Current/Best: 13.06/ 19.55 GFLOPS | Progress: (16/20) | 12.07 s
-[Task 20/25] Current/Best: 4.96/ 19.55 GFLOPS | Progress: (20/20) | 16.26 s
+[Task 20/25] Current/Best: 10.92/ 18.64 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 20/25] Current/Best: 7.56/ 18.64 GFLOPS | Progress: (8/20) | 5.30 s
+[Task 20/25] Current/Best: 13.03/ 18.64 GFLOPS | Progress: (12/20) | 8.68 s
+[Task 20/25] Current/Best: 4.75/ 18.64 GFLOPS | Progress: (16/20) | 12.25 s
+[Task 20/25] Current/Best: 17.66/ 18.64 GFLOPS | Progress: (20/20) | 14.99 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 14.43/ 14.43 GFLOPS | Progress: (4/20) | 2.68 s
-[Task 21/25] Current/Best: 10.62/ 16.52 GFLOPS | Progress: (8/20) | 4.70 s
-[Task 21/25] Current/Best: 15.53/ 18.16 GFLOPS | Progress: (12/20) | 6.21 s
-[Task 21/25] Current/Best: 8.50/ 18.16 GFLOPS | Progress: (16/20) | 8.25 s
-[Task 21/25] Current/Best: 9.44/ 18.16 GFLOPS | Progress: (20/20) | 10.56 s
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 22/25] Current/Best: 12.54/ 16.80 GFLOPS | Progress: (4/20) | 4.93 s
-[Task 22/25] Current/Best: 21.11/ 21.11 GFLOPS | Progress: (8/20) | 7.04 s
-[Task 22/25] Current/Best: 11.57/ 21.11 GFLOPS | Progress: (12/20) | 9.40 s
-[Task 22/25] Current/Best: 14.02/ 21.11 GFLOPS | Progress: (16/20) | 11.58 s
-[Task 22/25] Current/Best: 8.76/ 21.11 GFLOPS | Progress: (20/20) | 14.33 s Done.
+[Task 21/25] Current/Best: 13.69/ 13.69 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 21/25] Current/Best: 10.17/ 13.69 GFLOPS | Progress: (8/20) | 6.01 s
+[Task 21/25] Current/Best: 15.72/ 19.89 GFLOPS | Progress: (12/20) | 8.09 s Done.
+
+[Task 21/25] Current/Best: 19.17/ 19.89 GFLOPS | Progress: (16/20) | 10.64 s
+[Task 21/25] Current/Best: 11.50/ 19.89 GFLOPS | Progress: (20/20) | 13.01 s
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 22/25] Current/Best: 10.54/ 15.25 GFLOPS | Progress: (4/20) | 3.90 s
+[Task 22/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (8/20) | 5.78 s
+[Task 22/25] Current/Best: 2.66/ 18.23 GFLOPS | Progress: (12/20) | 7.75 s
+[Task 22/25] Current/Best: 12.71/ 18.78 GFLOPS | Progress: (16/20) | 9.39 s
+[Task 22/25] Current/Best: 6.94/ 18.78 GFLOPS | Progress: (20/20) | 13.00 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 7.67/ 22.71 GFLOPS | Progress: (4/20) | 3.74 s
-[Task 23/25] Current/Best: 10.84/ 22.71 GFLOPS | Progress: (8/20) | 5.86 s
-[Task 23/25] Current/Best: 11.27/ 22.71 GFLOPS | Progress: (12/20) | 8.13 s
-[Task 23/25] Current/Best: 9.48/ 22.71 GFLOPS | Progress: (16/20) | 10.50 s
-[Task 23/25] Current/Best: 21.34/ 22.71 GFLOPS | Progress: (20/20) | 13.49 s Done.
+[Task 23/25] Current/Best: 10.52/ 13.19 GFLOPS | Progress: (4/20) | 5.35 s
+[Task 23/25] Current/Best: 12.46/ 17.66 GFLOPS | Progress: (8/20) | 8.71 s
+[Task 23/25] Current/Best: 22.41/ 22.41 GFLOPS | Progress: (12/20) | 10.94 s
+[Task 23/25] Current/Best: 14.30/ 23.38 GFLOPS | Progress: (16/20) | 13.19 s
+[Task 23/25] Current/Best: 1.55/ 23.38 GFLOPS | Progress: (20/20) | 16.70 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 7.83/ 7.83 GFLOPS | Progress: (4/20) | 12.21 s
-[Task 24/25] Current/Best: 10.24/ 10.34 GFLOPS | Progress: (8/20) | 23.77 s
-[Task 24/25] Current/Best: 8.90/ 10.34 GFLOPS | Progress: (12/20) | 35.06 s
-[Task 24/25] Current/Best: 2.54/ 10.34 GFLOPS | Progress: (16/20) | 46.69 s
-[Task 24/25] Current/Best: 9.31/ 10.34 GFLOPS | Progress: (20/20) | 58.33 s
+[Task 24/25] Current/Best: 3.67/ 4.00 GFLOPS | Progress: (4/20) | 12.29 s
+[Task 24/25] Current/Best: 5.96/ 5.96 GFLOPS | Progress: (8/20) | 22.97 s
+[Task 24/25] Current/Best: 3.69/ 5.96 GFLOPS | Progress: (12/20) | 34.59 s
+[Task 24/25] Current/Best: 8.01/ 8.01 GFLOPS | Progress: (16/20) | 40.69 s
+[Task 24/25] Current/Best: 9.98/ 10.19 GFLOPS | Progress: (20/20) | 51.20 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-[Task 25/25] Current/Best: 1.55/ 6.40 GFLOPS | Progress: (4/20) | 4.58 s
-[Task 25/25] Current/Best: 6.43/ 8.25 GFLOPS | Progress: (8/20) | 6.59 s
-[Task 25/25] Current/Best: 6.11/ 8.25 GFLOPS | Progress: (12/20) | 11.17 s
-[Task 25/25] Current/Best: 1.55/ 8.25 GFLOPS | Progress: (16/20) | 21.92 s
-[Task 25/25] Current/Best: 9.62/ 9.62 GFLOPS | Progress: (20/20) | 26.83 s
+[Task 25/25] Current/Best: 1.54/ 8.00 GFLOPS | Progress: (4/20) | 12.25 s
+[Task 25/25] Current/Best: 5.02/ 8.00 GFLOPS | Progress: (8/20) | 17.43 s
+[Task 25/25] Current/Best: 8.36/ 8.36 GFLOPS | Progress: (12/20) | 18.81 s
+[Task 25/25] Current/Best: 9.44/ 9.44 GFLOPS | Progress: (16/20) | 20.93 s
+[Task 25/25] Current/Best: 1.55/ 9.44 GFLOPS | Progress: (20/20) | 31.63 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -945,8 +944,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -983,8 +982,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 409.97064049000073, 'median': 409.4862530499995, 'std': 1.3765838115104683}
-unoptimized: {'mean': 510.6892897400006, 'median': 510.96751540000014, 'std': 1.8923402940276843}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 395.1927164298104, 'median': 394.8172410000552, 'std': 1.0674296433254005}
+unoptimized: {'mean': 513.2742928301741, 'median': 513.4689666498161, 'std': 1.5081723780732224}
</pre></div>
</div>
</div>
@@ -998,7 +997,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 8.730 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 24.491 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index be46ffd200..22691de7a4 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.256e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.247e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 679671fe87..67c162ea48 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -497,7 +497,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xde69960)), stage(b, placeholder(b, 0xe3686e0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[it [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x22c264a0)), stage(b, placeholder(b, 0x5bde450)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 1aab5d05a9..921920a9f9 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:39.169</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:17.749</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>11:08.730</p></td>
+<td><p>10:24.491</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:25.906</p></td>
+<td><p>01:35.299</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.358</p></td>
+<td><p>00:58.276</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:37.962</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
+<td><p>00:41.458</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:22.915</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
+<td><p>00:36.428</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.307</p></td>
+<td><p>00:00.817</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.816</p></td>
+<td><p>00:00.790</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.168</p></td>
+<td><p>00:00.179</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 97055317db..0611bf32cb 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -552,7 +552,7 @@ helper function to run a profile of the TVM generated code.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000008
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -601,7 +601,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000009
</pre></div>
</div>
</div>
@@ -673,10 +673,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.69521000165696e-06 1.0
- naive 8.1393e-06 1.0577099258171534
-parallel 8.1727e-06 1.0620502881974925
- vector 2.45548e-05 3.190920065172071
+ numpy 7.64272001106292e-06 1.0
+ naive 6.6855e-06 0.8747540130114234
+parallel 8.909300000000001e-06 1.1657237197102202
+ vector 2.45727e-05 3.2151773144156466
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -992,7 +992,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018264
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018447
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1033,7 +1033,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.453191
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.197408
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1098,7 +1098,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.294637
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.297889
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1157,7 +1157,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.331969
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.335439
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1212,7 +1212,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.117642
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116555
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1288,7 +1288,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109222
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108118
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1362,7 +1362,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110735
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.109582
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1429,7 +1429,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145618
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145101
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4531908412999996 1.0
- blocking 0.2946366399 0.08532301093126962
- vectorization 0.3319694918 0.0961341284210709
... 22 lines suppressed ...