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 2022/04/04 21:47:37 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@c2744704bec3cc914fa96dc4f4c9b0ccfaa8ace4)
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 ae90a2f8b deploying docs (apache/tvm@c2744704bec3cc914fa96dc4f4c9b0ccfaa8ace4)
ae90a2f8b is described below
commit ae90a2f8b08f2a87f3f1af1954003ff5f7d33428
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Apr 4 21:47:33 2022 +0000
deploying docs (apache/tvm@c2744704bec3cc914fa96dc4f4c9b0ccfaa8ace4)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_onnx.rst.txt | 11 +
.../how_to/compile_models/from_paddle.rst.txt | 21 +-
.../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 | 20 +-
.../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 | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 1763 ++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 263 ++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 4 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 57 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 38 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_onnx.html | 7 +
docs/how_to/compile_models/from_paddle.html | 17 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 20 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 41 +-
docs/how_to/deploy_models/deploy_prequantized.html | 11 +-
.../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 | 38 +-
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 | 1763 ++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 263 ++-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 4 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_relay_x86.html | 167 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 38 +-
115 files changed, 4091 insertions(+), 1484 deletions(-)
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 bb78ba2cb..be7749ee3 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb1ef4cfb-7e93-4c74-8d67-82a960906f6d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip795bd19e-2151-46c5-94a6-56116b9f665b 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_onnx.rst.txt b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
index 5fa0e060b..883146ab2 100644
--- a/docs/_sources/how_to/compile_models/from_onnx.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
@@ -178,6 +178,17 @@ bicubic algorithm. The image is then recombined and converted back to `RGB`.
:class: sphx-glr-single-img
+.. rst-class:: sphx-glr-script-out
+
+ Out:
+
+ .. code-block:: none
+
+ /workspace/gallery/how_to/compile_models/from_onnx.py:114: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
+ out_cb = img_cb.resize(out_y.size, Image.BICUBIC)
+ /workspace/gallery/how_to/compile_models/from_onnx.py:115: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
+ out_cr = img_cr.resize(out_y.size, Image.BICUBIC)
+
Notes
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 7c7e42eeb..becab8b1b 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -36,6 +36,25 @@ https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/inst
+.. rst-class:: sphx-glr-script-out
+
+ Out:
+
+ .. code-block:: none
+
+ /usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:36: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.NEAREST or Dither.NONE instead.
+ 'nearest': Image.NEAREST,
+ /usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:37: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
+ 'bilinear': Image.BILINEAR,
+ /usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:38: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
+ 'bicubic': Image.BICUBIC,
+ /usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:39: DeprecationWarning: BOX is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BOX instead.
+ 'box': Image.BOX,
+ /usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:40: DeprecationWarning: LANCZOS is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.LANCZOS instead.
+ 'lanczos': Image.LANCZOS,
+ /usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:41: DeprecationWarning: HAMMING is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.HAMMING instead.
+ 'hamming': Image.HAMMING
+
Load pretrained ResNet50 model
@@ -182,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.476 seconds)
+ **Total running time of the script:** ( 1 minutes 4.747 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
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 f13335912..9049ba78b 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ Load a pretrained PyTorch model
.. code-block:: none
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]
17%|#6 | 7.58M/44.7M [00:00<00:00, 79.5MB/s]
59%|#####9 | 26.5M/44.7M [00:00<00:00, 149MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 159MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
26%|##5 | 11.5M/44.7M [00:00<00:00, 121MB/s]
67%|######6 | 29.7M/44.7M [00:00<00:00, 162MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 166MB/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 1623750dd..15ad08e1a 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -372,7 +372,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.350 seconds)
+ **Total running time of the script:** ( 1 minutes 0.138 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 caae71204..d65c68708 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
@@ -5,14 +5,14 @@
Computation times
=================
-**04:48.458** total execution time for **how_to_compile_models** files:
+**04:47.919** total execution time for **how_to_compile_models** files:
-- **01:05.476**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:01.350**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:56.199**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:25.924**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.935**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:21.349**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:19.504**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.059**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.663**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:04.747**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:00.138**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:56.256**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:27.554**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.088**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:21.056**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:19.118**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:15.492**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.469**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
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 864e68f13..b1d5df6a6 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
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0546 16.0586 16.3876 15.6943 0.1770
+ 15.8478 15.7898 16.1872 15.7288 0.1350
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 7e5619fac..78918c191 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
@@ -108,7 +108,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
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]
1%|1 | 2.38M/170M [00:00<00:07, 23.5MB/s]
3%|3 | 5.42M/170M [00:00<00:06, 26.2MB/s]
5%|4 | 8.09M/170M [00:00<00:06, 26.7MB/s]
6%|6 | 10.6M/170M [00:00<00:06, 24.6MB/s]
10%|9 | 16.4M/170M [00:00<00:04, 36.4MB/s]
12%|#1 | 20.1M/170M [00:00<00:04, 35.8MB/s]
16%|#6 | 27.7M/170M [00:00<00:03, 49.4MB/s]
20%|#9 | 33.4M/170M [00:00<00:02, 52.6MB/s]
23%|##2 | 38.7M/170M [00:00<00:02, 53.2MB/s]
27%|##7 | 46.5M/170M [00:01<00:02, 61.8MB/s]
33%|###2 | 55.3M/170M [00:01<00:01, 70.9MB/s]
37%|###6 | 62.1M/170M [00:01<00:01, 61.7MB/s]
42%|####1 | 71.3M/170M [00:01<00:01, 71.2MB/s]
46%|####6 | 78.4M/170M [00:01<00:01, 71.1MB/s]
50%|##### | 85.4M/170M [00:01<00:01, 58.0MB/s]
54%|#####3 | 91.4M/170M [00:01<00:01, 52.2MB/s]
58%|#####8 | 98.9M/170M [00:01<00:01, 58.3MB/
s]
63%|######2 | 107M/170M [00:02<00:01, 63.9MB/s]
67%|######7 | 114M/170M [00:02<00:00, 66.7MB/s]
71%|#######1 | 121M/170M [00:02<00:00, 69.4MB/s]
77%|#######6 | 130M/170M [00:02<00:00, 75.1MB/s]
81%|######## | 137M/170M [00:02<00:00, 66.5MB/s]
85%|########5 | 145M/170M [00:02<00:00, 70.3MB/s]
90%|########9 | 152M/170M [00:02<00:00, 60.6MB/s]
93%|#########3| 158M/170M [00:02<00:00, 54.2MB/s]
96%|#########6| 164M/170M [00:03<00:00, 52.7MB/s]
100%|#########9| 170M/170M [00:03<00:00, 55.0MB/s]
100%|##########| 170M/170M [00:03<00:00, 56.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
6%|6 | 10.4M/170M [00:00<00:01, 109MB/s]
15%|#4 | 25.0M/170M [00:00<00:01, 135MB/s]
25%|##4 | 42.1M/170M [00:00<00:00, 155MB/s]
35%|###4 | 59.4M/170M [00:00<00:00, 165MB/s]
45%|####5 | 76.6M/170M [00:00<00:00, 170MB/s]
55%|#####5 | 94.0M/170M [00:00<00:00, 175MB/s]
66%|######5 | 111M/170M [00:00<00:00, 177MB/s]
76%|#######5 | 129M/170M [00:00<00:00, 178MB/s]
86%|########5 | 146M/170M [00:00<00:00, 179MB/s]
96%|#########5| 163M/170M [00:01<00:00, 179MB/s]
100%|##########| 170M/170M [00:01<00:00, 171MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: 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)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: 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').
@@ -253,7 +253,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 10.430 seconds)
+ **Total running time of the script:** ( 3 minutes 1.658 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 a263eeb6a..b9f8331bb 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
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]
38%|###7 | 5.14M/13.6M [00:00<00:00, 53.8MB/s]
100%|#########9| 13.5M/13.6M [00:00<00:00, 73.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 70.8MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
31%|###1 | 4.21M/13.6M [00:00<00:00, 44.1MB/s]
62%|######2 | 8.41M/13.6M [00:00<00:00, 39.1MB/s]
97%|#########7| 13.2M/13.6M [00:00<00:00, 43.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 42.8MB/s]
@@ -344,7 +344,7 @@ 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)
- 90.2897 90.1839 93.8210 90.0559 0.4222
+ 90.3214 90.1819 101.8479 89.8892 1.1982
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.783 seconds)
+ **Total running time of the script:** ( 1 minutes 3.963 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 85208d12b..c3d9bb8fa 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
@@ -351,7 +351,7 @@ 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)
- 120.1680 120.1239 123.2265 119.4900 0.4609
+ 119.2355 119.2110 120.7470 118.3210 0.4406
@@ -385,7 +385,7 @@ 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:** ( 1 minutes 58.866 seconds)
+ **Total running time of the script:** ( 2 minutes 1.184 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 a1dd6e9fb..cf84b46c4 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 45.802 seconds)
+ **Total running time of the script:** ( 1 minutes 25.381 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 451983bbb..c2bcb9fc0 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
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5778/132723 [00:00<00:02, 57776.06KB/s]
10%|# | 13486/132723 [00:00<00:01, 69122.61KB/s]
16%|#5 | 21213/132723 [00:00<00:01, 72839.43KB/s]
22%|##1 | 28897/132723 [00:00<00:01, 74382.39KB/s]
27%|##7 | 36496/132723 [00:00<00:01, 74959.67KB/s]
34%|###3 | 44482/132723 [00:00<00:01, 76622.52KB/s]
40%|###9 | 52523/132723 [00:00<00:01, 77853.30KB/s]
46%|####5 | 60640/132723 [00:00<00:00, 78904.86KB/s]
52%|#####1 | 68714/132723 [00:00<00:00, 79476.52KB/s]
58%|#####7 | 76849/132723 [00:01<00:00, 80053.20KB/s]
64%|######4 | 84958/132723 [00:01<00:00, 80368.51KB/s]
70%|####### | 93122/132723 [00:01<00:00, 80753.42KB/s]
76%|#######6 | 101269/132723 [00:01<00:00, 80968.11KB/s]
82%|########2 | 109416/132723 [00:01<00:00, 81117.20KB/s]
89%|########8 | 117602/132723 [00:01<00:00, 81338.66KB/s]
95%|########
#4| 125743/132723 [00:01<00:00, 81357.76KB/s]
100%|##########| 132723/132723 [00:01<00:00, 78708.31KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5009/132723 [00:00<00:02, 50077.15KB/s]
9%|9 | 12105/132723 [00:00<00:01, 62354.76KB/s]
15%|#4 | 19816/132723 [00:00<00:01, 69087.52KB/s]
21%|## | 27624/132723 [00:00<00:01, 72634.39KB/s]
26%|##6 | 34888/132723 [00:00<00:01, 59341.22KB/s]
31%|###1 | 41148/132723 [00:00<00:01, 51108.96KB/s]
36%|###5 | 47389/132723 [00:00<00:01, 54090.97KB/s]
40%|#### | 53102/132723 [00:00<00:01, 50008.92KB/s]
44%|####3 | 58335/132723 [00:01<00:01, 49509.75KB/s]
50%|####9 | 66063/132723 [00:01<00:01, 56960.31KB/s]
56%|#####5 | 73779/132723 [00:01<00:00, 62557.99KB/s]
61%|######1 | 81613/132723 [00:01<00:00, 67031.93KB/s]
67%|######7 | 89470/132723 [00:01<00:00, 70353.65KB/s]
73%|#######3 | 97278/132723 [00:01<00:00, 72605.57KB/s]
79%|#######9 | 105042/132723 [00:01<00:00, 74085.33KB/s]
85%|########5
| 112865/132723 [00:01<00:00, 75308.78KB/s]
91%|######### | 120717/132723 [00:01<00:00, 76237.20KB/s]
97%|#########6| 128544/132723 [00:01<00:00, 76841.47KB/s]
100%|##########| 132723/132723 [00:02<00:00, 65703.53KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 23.727 seconds)
+ **Total running time of the script:** ( 2 minutes 20.711 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 721454db0..fe8cd43b2 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
@@ -5,13 +5,13 @@
Computation times
=================
-**11:14.502** total execution time for **how_to_deploy_models** files:
+**10:42.517** total execution time for **how_to_deploy_models** files:
-- **03:10.430**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:23.727**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:58.866**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:45.802**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:05.783**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:27.853**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:21.846**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.194**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:01.658**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:20.711**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **02:01.184**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:25.381**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:03.963**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.654**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.784**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.184**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
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 4015f6e0f..e03f8a5dc 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
@@ -423,7 +423,7 @@ 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.zip18d6b82f-2221-4365-980d-325aec9223b1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip945f3aed-ce8d-4ab0-aed1-a30043a26a46 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 fce7e2e6b..f0512e0d1 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
@@ -5,9 +5,9 @@
Computation times
=================
-**00:38.410** total execution time for **how_to_extend_tvm** files:
+**00:37.362** total execution time for **how_to_extend_tvm** files:
-- **00:34.887**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.255**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.065**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.203**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:33.959**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.195**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.018**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.191**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
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 0263c3cb4..ae0ad99f4 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
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 5974us [5974us] (45.52%; 45.52%)
- FoldScaleAxis: 7150us [2us] (54.48%; 54.48%)
- FoldConstant: 7147us [1461us] (54.46%; 99.97%)
- InferType: 5686us [5686us] (43.33%; 79.55%)
+ InferType: 5933us [5933us] (45.43%; 45.43%)
+ FoldScaleAxis: 7128us [2us] (54.57%; 54.57%)
+ FoldConstant: 7126us [1487us] (54.55%; 99.97%)
+ InferType: 5638us [5638us] (43.17%; 79.13%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 5743us [5743us] (44.57%; 44.57%)
- FoldScaleAxis: 7142us [2us] (55.43%; 55.43%)
- FoldConstant: 7139us [1504us] (55.41%; 99.97%)
- InferType: 5635us [5635us] (43.74%; 78.93%)
+ InferType: 5713us [5713us] (44.30%; 44.30%)
+ FoldScaleAxis: 7183us [2us] (55.70%; 55.70%)
+ FoldConstant: 7180us [1517us] (55.68%; 99.97%)
+ InferType: 5664us [5664us] (43.92%; 78.88%)
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 1410b4411..61407e516 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
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 51.561264 ms
+ Convolution: 40.672973 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 3434e47fb..4a23bc3a0 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
@@ -626,7 +626,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 9.854424 ms
+ conv2d with tensor core: 10.197852 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 3eef3c5b4..f57054c25 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018808
- Baseline: 3.260891
+ Numpy running time: 0.018419
+ Baseline: 3.195817
@@ -209,7 +209,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.311549
+ Opt1: 0.297370
@@ -307,7 +307,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.341674
+ Opt2: 0.333479
@@ -398,7 +398,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116943
+ Opt3: 0.115630
@@ -516,7 +516,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110352
+ Opt4: 0.110539
@@ -633,7 +633,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111289
+ Opt5: 0.110639
@@ -753,7 +753,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145131
+ Opt6: 0.144140
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 718f45aaa..8172f2389 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:34.846** total execution time for **how_to_optimize_operators** files:
+**00:34.203** total execution time for **how_to_optimize_operators** files:
-- **00:32.196**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.425**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.225**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:31.573**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.427**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.203**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
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 fe21e8ae1..5de6e807c 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
@@ -5,11 +5,11 @@
Computation times
=================
-**04:56.081** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:21.190**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:20.183**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.548**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:16.893**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.793**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.475**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:53.263** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:20.559**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:19.357**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:39.826**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:16.849**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.454**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.218**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
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 8915f7de2..cfd9ef6c8 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
@@ -221,11 +221,11 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), 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" = 224 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -233,156 +233,736 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 256) {
- let cse_var_2: int32 = (rc.outer.outer*98)
- let cse_var_1: int32 = (rc.outer.outer*18)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 31), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ for (rc.outer.outer: int32, 0, 16) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 32), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 64), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 96), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 128), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, d [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 160), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 192), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 256), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 7), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 14), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 28), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 35), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 49), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 56), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 70), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 77), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_2 < 160), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 91), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 75)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 76)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 78)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 79)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 80)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 633)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 634)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 635)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 636)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 696)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 697)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 698)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 699)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 759)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 760)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 761)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 762)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 885)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 886)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 887)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 888)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 948)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 949)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 950)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 951)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1009)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1010)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1011)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1012)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1013)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1014)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1016)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1017)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1018)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1019)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1020)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1021)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1023)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1024)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1025)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1026)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1027)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1028)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1079)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1080)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1081)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1082)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1083)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1084)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1086)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1087)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1088)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1089)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1090)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1091)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1210)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1212)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1213)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1214)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1273)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1275)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1276)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1277)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1278)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1399)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1401)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1402)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1403)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1404)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1462)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1464)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1465)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1466)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1467)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1525)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1527)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1528)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1529)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1530)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1655)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1656)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1714)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1716)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1717)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1718)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1719)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1720)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1721)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1777)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1779)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1780)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1781)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1782)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1783)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1784)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1840)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1842)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1843)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1844)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1845)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1846)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1847)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1907)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1908)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1966)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1968)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1969)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1970)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1971)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 2) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
- 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 + 112)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 2) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
}
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -435,7 +1015,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.318 ms
+ Execution time of this operator: 0.410 ms
@@ -481,34 +1061,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
conv2d_nchw_ff_o_o_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=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_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
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_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_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_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
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=3)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
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=7)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_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_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)
@@ -528,12 +1108,12 @@ 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=56)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
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", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -553,10 +1133,10 @@ 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__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[162];
- __shared__ float kernel_shared[144];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -564,148 +1144,711 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((int)threadIdx.x) < 41) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 129024)];
+ if (((int)threadIdx.x) < 160) {
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 75)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 76)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 77)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 78)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 79)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 80)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 633)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 634)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 635)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 636)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 637)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 696)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 697)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 698)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 699)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 700)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 759)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 760)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 761)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 762)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 763)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 885)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 886)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 887)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 888)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 889)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 948)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 949)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 950)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 951)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 952)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1011)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1012)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1013)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1014)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1016)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1017)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1018)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1019)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1020)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1021)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1023)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1024)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1025)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1026)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1027)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1028)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1079)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1080)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1081)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1082)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1083)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1084)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1086)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1087)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1088)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1089)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1090)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1091)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1210)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1212)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1213)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1214)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1273)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1275)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1276)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1277)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1278)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1399)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1401)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1402)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1403)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1404)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1462)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1464)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1465)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1466)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1467)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1525)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1527)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1528)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1529)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1530)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1655)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1656)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1714)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1716)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1717)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1718)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1719)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1720)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1721)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1777)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1779)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1780)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1781)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1782)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1783)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1784)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1840)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1842)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1843)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1844)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1845)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1846)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1847)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1907)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1908)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1966)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1968)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1969)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1970)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1971)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
@@ -764,7 +1907,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 21.190 seconds)
+ **Total running time of the script:** ( 2 minutes 20.559 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 42d3aaeaf..4a09be2bc 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
@@ -614,7 +614,7 @@ 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)
- 9.9008 9.9027 9.9199 9.8797 0.0165
+ 9.7098 9.7199 9.7400 9.6697 0.0296
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 4cbfc9ea1..e5630d0b8 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
@@ -633,7 +633,7 @@ 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)
- 770.2555 771.6021 776.6457 762.5187 5.8454
+ 759.2196 758.9126 765.6314 753.1150 5.1144
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.183 seconds)
+ **Total running time of the script:** ( 1 minutes 19.357 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 05f88d410..894d9357f 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
@@ -364,75 +364,214 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
- compute_4[(cse_var_1 + 1)] = 0f32
- compute_4[(cse_var_1 + 2)] = 0f32
- compute_4[(cse_var_1 + 3)] = 0f32
- compute_4[(cse_var_1 + 4)] = 0f32
- compute_4[(cse_var_1 + 5)] = 0f32
- compute_4[(cse_var_1 + 6)] = 0f32
- compute_4[(cse_var_1 + 7)] = 0f32
- compute_4[(cse_var_1 + 8)] = 0f32
- compute_4[(cse_var_1 + 9)] = 0f32
- compute_4[(cse_var_1 + 10)] = 0f32
- compute_4[(cse_var_1 + 11)] = 0f32
- compute_4[(cse_var_1 + 12)] = 0f32
- compute_4[(cse_var_1 + 13)] = 0f32
- compute_4[(cse_var_1 + 14)] = 0f32
- compute_4[(cse_var_1 + 15)] = 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, 8) {
- 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*2048) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 1)
- let cse_var_16: int32 = (cse_var_18 + 11)
- let cse_var_15: int32 = (cse_var_18 + 12)
- let cse_var_14: int32 = (cse_var_18 + 13)
- let cse_var_13: int32 = (cse_var_18 + 14)
- let cse_var_12: int32 = (cse_var_18 + 15)
- let cse_var_11: int32 = (cse_var_18 + 2)
- let cse_var_10: int32 = (cse_var_18 + 3)
- let cse_var_9: int32 = (cse_var_18 + 4)
- let cse_var_8: int32 = (cse_var_18 + 5)
- let cse_var_7: int32 = (cse_var_18 + 6)
- let cse_var_6: int32 = (cse_var_18 + 7)
- let cse_var_5: int32 = (cse_var_18 + 8)
- let cse_var_4: int32 = (cse_var_18 + 9)
- let cse_var_3: int32 = (cse_var_18 + 10)
+ let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ compute_4[(cse_var_1 + 32)] = 0f32
+ compute_4[(cse_var_1 + 33)] = 0f32
+ compute_4[(cse_var_1 + 34)] = 0f32
+ compute_4[(cse_var_1 + 35)] = 0f32
+ compute_4[(cse_var_1 + 36)] = 0f32
+ compute_4[(cse_var_1 + 37)] = 0f32
+ compute_4[(cse_var_1 + 38)] = 0f32
+ compute_4[(cse_var_1 + 39)] = 0f32
+ compute_4[(cse_var_1 + 40)] = 0f32
+ compute_4[(cse_var_1 + 41)] = 0f32
+ compute_4[(cse_var_1 + 42)] = 0f32
+ compute_4[(cse_var_1 + 43)] = 0f32
+ compute_4[(cse_var_1 + 44)] = 0f32
+ compute_4[(cse_var_1 + 45)] = 0f32
+ compute_4[(cse_var_1 + 46)] = 0f32
+ compute_4[(cse_var_1 + 47)] = 0f32
+ compute_4[(cse_var_1 + 64)] = 0f32
+ compute_4[(cse_var_1 + 65)] = 0f32
+ compute_4[(cse_var_1 + 66)] = 0f32
+ compute_4[(cse_var_1 + 67)] = 0f32
+ compute_4[(cse_var_1 + 68)] = 0f32
+ compute_4[(cse_var_1 + 69)] = 0f32
+ compute_4[(cse_var_1 + 70)] = 0f32
+ compute_4[(cse_var_1 + 71)] = 0f32
+ compute_4[(cse_var_1 + 72)] = 0f32
+ compute_4[(cse_var_1 + 73)] = 0f32
+ compute_4[(cse_var_1 + 74)] = 0f32
+ compute_4[(cse_var_1 + 75)] = 0f32
+ compute_4[(cse_var_1 + 76)] = 0f32
+ compute_4[(cse_var_1 + 77)] = 0f32
+ compute_4[(cse_var_1 + 78)] = 0f32
+ compute_4[(cse_var_1 + 79)] = 0f32
+ compute_4[(cse_var_1 + 96)] = 0f32
+ compute_4[(cse_var_1 + 97)] = 0f32
+ compute_4[(cse_var_1 + 98)] = 0f32
+ compute_4[(cse_var_1 + 99)] = 0f32
+ compute_4[(cse_var_1 + 100)] = 0f32
+ compute_4[(cse_var_1 + 101)] = 0f32
+ compute_4[(cse_var_1 + 102)] = 0f32
+ compute_4[(cse_var_1 + 103)] = 0f32
+ compute_4[(cse_var_1 + 104)] = 0f32
+ compute_4[(cse_var_1 + 105)] = 0f32
+ compute_4[(cse_var_1 + 106)] = 0f32
+ compute_4[(cse_var_1 + 107)] = 0f32
+ compute_4[(cse_var_1 + 108)] = 0f32
+ compute_4[(cse_var_1 + 109)] = 0f32
+ compute_4[(cse_var_1 + 110)] = 0f32
+ compute_4[(cse_var_1 + 111)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ let cse_var_67: int32 = (cse_var_1 + 41)
+ let cse_var_66: int32 = (cse_var_1 + 40)
+ let cse_var_65: int32 = (cse_var_1 + 4)
+ let cse_var_64: int32 = (cse_var_1 + 39)
+ let cse_var_63: int32 = (cse_var_1 + 38)
+ let cse_var_62: int32 = (cse_var_1 + 37)
+ let cse_var_61: int32 = (cse_var_1 + 36)
+ let cse_var_60: int32 = (cse_var_1 + 35)
+ let cse_var_59: int32 = (cse_var_1 + 34)
+ let cse_var_58: int32 = (cse_var_1 + 33)
+ let cse_var_57: int32 = (cse_var_1 + 32)
+ let cse_var_56: int32 = (cse_var_1 + 3)
+ let cse_var_55: int32 = (cse_var_1 + 2)
+ let cse_var_54: int32 = (cse_var_1 + 15)
+ let cse_var_53: int32 = (cse_var_1 + 14)
+ let cse_var_52: int32 = (cse_var_1 + 1)
+ let cse_var_51: int32 = (cse_var_1 + 12)
+ let cse_var_50: int32 = (cse_var_1 + 111)
+ let cse_var_49: int32 = (cse_var_1 + 110)
+ let cse_var_48: int32 = (cse_var_1 + 11)
+ let cse_var_47: int32 = (cse_var_1 + 109)
+ let cse_var_46: int32 = (cse_var_1 + 108)
+ let cse_var_45: int32 = (cse_var_1 + 107)
+ let cse_var_44: int32 = (cse_var_1 + 106)
+ let cse_var_43: int32 = (cse_var_1 + 105)
+ let cse_var_42: int32 = (cse_var_1 + 104)
+ let cse_var_41: int32 = (cse_var_1 + 103)
+ let cse_var_40: int32 = (cse_var_1 + 102)
+ let cse_var_39: int32 = (cse_var_1 + 101)
+ let cse_var_38: int32 = (cse_var_1 + 100)
+ let cse_var_37: int32 = (cse_var_1 + 10)
+ let cse_var_36: int32 = (cse_var_1 + 13)
+ let cse_var_35: int32 = (i.outer.inner*1024)
+ let cse_var_34: int32 = (elem_idx*16)
+ let cse_var_33: int32 = (cse_var_1 + 99)
+ let cse_var_32: int32 = (cse_var_1 + 98)
+ let cse_var_31: int32 = (cse_var_1 + 97)
+ let cse_var_30: int32 = (cse_var_1 + 96)
+ let cse_var_29: int32 = (cse_var_1 + 9)
+ let cse_var_28: int32 = (cse_var_1 + 8)
+ let cse_var_27: int32 = (cse_var_1 + 79)
+ let cse_var_26: int32 = (cse_var_1 + 78)
+ let cse_var_25: int32 = (cse_var_1 + 77)
+ let cse_var_24: int32 = (cse_var_1 + 76)
+ let cse_var_23: int32 = (cse_var_1 + 75)
+ let cse_var_22: int32 = (cse_var_1 + 74)
+ let cse_var_21: int32 = (cse_var_1 + 73)
+ let cse_var_20: int32 = (cse_var_1 + 42)
+ let cse_var_19: int32 = (cse_var_1 + 43)
+ let cse_var_18: int32 = (cse_var_1 + 44)
+ let cse_var_17: int32 = (cse_var_1 + 45)
+ let cse_var_16: int32 = (cse_var_1 + 46)
+ let cse_var_15: int32 = (cse_var_1 + 47)
+ let cse_var_14: int32 = (cse_var_1 + 5)
+ let cse_var_13: int32 = (cse_var_1 + 6)
+ let cse_var_12: int32 = (cse_var_1 + 72)
+ let cse_var_11: int32 = (cse_var_1 + 65)
+ let cse_var_10: int32 = (cse_var_1 + 66)
+ let cse_var_9: int32 = (cse_var_1 + 67)
+ let cse_var_8: int32 = (cse_var_1 + 68)
+ let cse_var_7: int32 = (cse_var_1 + 69)
+ let cse_var_6: int32 = (cse_var_1 + 7)
+ let cse_var_5: int32 = (cse_var_1 + 70)
+ let cse_var_4: int32 = (cse_var_1 + 71)
+ let cse_var_3: int32 = (cse_var_1 + 64)
{
- compute_4[cse_var_18] = (compute_4[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_4[cse_var_17] = (compute_4[cse_var_17] + (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_4[cse_var_11] = (compute_4[cse_var_11] + (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_4[cse_var_10] = (compute_4[cse_var_10] + (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_4[cse_var_9] = (compute_4[cse_var_9] + (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_4[cse_var_8] = (compute_4[cse_var_8] + (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_4[cse_var_7] = (compute_4[cse_var_7] + (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_4[cse_var_6] = (compute_4[cse_var_6] + (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_4[cse_var_5] = (compute_4[cse_var_5] + (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_4[cse_var_4] = (compute_4[cse_var_4] + (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_4[cse_var_3] = (compute_4[cse_var_3] + (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_4[cse_var_16] = (compute_4[cse_var_16] + (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_4[cse_var_15] = (compute_4[cse_var_15] + (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_4[cse_var_14] = (compute_4[cse_var_14] + (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_4[cse_var_13] = (compute_4[cse_var_13] + (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_4[cse_var_12] = (compute_4[cse_var_12] + (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)))
+ compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 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_4[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ let cse_var_68: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_68, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -486,7 +625,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.856 ms
+ Execution time of this operator: 3.026 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 c5334535a..663221b45 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.076** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.101** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.226**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.222**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.210**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.209**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.209**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:43.285**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.202**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.200**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.199**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
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 3d8d79746..0f0585639 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
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.29/42.29 result: MeasureResult(costs=(0.005474721105263158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5929961204528809, timestamp=1649040668.6649668) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 103.38/103.38 result: MeasureResult(costs=(0.0022393124791666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5896687507629395, timestamp=1649098570.4953766) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fabcb57bfa2
+ 12: 0x00007f5adc41dfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 144.34/144.34 result: MeasureResult(costs=(0.0016038595799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4119071960449219, timestamp=1649040694.311562) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 145.02/145.02 result: MeasureResult(costs=(0.00159632587,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4061989784240723, timestamp=1649098596.76297) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.002023
+ Time cost of this operator: 0.002075
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 c7d894000..5aeb51ef1 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
@@ -292,10 +292,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.2 98.749 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.963 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.289 (1, 1, 10, 10, 3) 1 1
- Total_time - 319.194 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.7 98.749 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.957 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.294 (1, 1, 10, 10, 3) 1 1
+ Total_time - 313.623 - - - -
@@ -357,10 +357,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 197.4 98.673 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.753 0.876 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.45 (1, 3, 10, 10, 1) 1 1
- Total_time - 200.054 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 124.2 97.839 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.414 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.949 0.748 (1, 1, 10, 10, 3) 1 1
+ Total_time - 126.944 - - - -
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 ddec2d94c..e1721a6fc 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.498** total execution time for **how_to_work_with_microtvm** files:
+**00:43.889** total execution time for **how_to_work_with_microtvm** files:
-- **00:40.422**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.488**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.197**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.195**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.195**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:39.919**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.415**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.187**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.185**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.182**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
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 5ed2afd9b..9373c7cbe 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:11.621** total execution time for **how_to_work_with_relay** files:
+**00:09.056** total execution time for **how_to_work_with_relay** files:
-- **00:07.623**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:03.783**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:07.209**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.650**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.198**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
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 8ec9fe18e..ebc5823a7 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
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.647** total execution time for **how_to_work_with_schedules** files:
+**00:05.530** total execution time for **how_to_work_with_schedules** files:
-- **00:02.047**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.176**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.718**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.701**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.309**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.237**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.237**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.221**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.048**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.142**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.699**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.689**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.293**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.223**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.210**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
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 2d12dad5c..e799f62d1 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -314,8 +314,8 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [32768], []),
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpw6mx02eu/input0.cc'
- source_filename = "/tmp/tmpw6mx02eu/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp4240yq0x/input0.cc'
+ source_filename = "/tmp/tmp4240yq0x/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
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 400cdcf36..51f28bd0f 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:19.850** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:19.668** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:19.644**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.207**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:19.479**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.190**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
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 fdbff841a..a91988e11 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ 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 21.11s!
+ resnet18_v1 inference graph built in 20.83s!
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 a81c16148..841cbd0eb 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 14.60s!
+ yolov3-tiny inference graph built in 14.29s!
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 18706aeb6..a479e91ea 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
@@ -5,7 +5,7 @@
Computation times
=================
-**01:27.654** total execution time for **topic_vta_tutorials_frontend** files:
+**01:27.009** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:46.529**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.125**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.170**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:40.839**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
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 2cbf3f228..869073f8f 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.501** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.474** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:02.965**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.536**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.952**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.521**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
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 c759fa0df..689f746a8 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:00.979** total execution time for **topic_vta_tutorials** files:
+**00:00.952** total execution time for **topic_vta_tutorials** files:
-- **00:00.495**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.483**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.483**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.469**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 77d6bce4b..96ca594f8 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -305,7 +305,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.508 ms
+ Execution time of this operator: 92.659 ms
@@ -401,7 +401,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ *E
@@ -414,6 +414,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 4.190 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 1daec761e..1b956d435 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -268,7 +268,7 @@ standard deviation.
.. code-block:: none
- {'mean': 496.7789972299988, 'median': 496.78255254999897, 'std': 0.7418708641711039}
+ {'mean': 488.3565407600014, 'median': 488.1888957000001, 'std': 0.7026204955701438}
@@ -482,31 +482,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 23.24/ 23.24 GFLOPS | Progress: (4/10) | 9.04 s
[Task 1/25] Current/Best: 11.68/ 23.24 GFLOPS | Progress: (8/10) | 14.55 s
[Task 1/25] Current/Best: 23.93/ 23.93 GFLOPS | Progress: (10/10) | 15.53 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 19.19/ 19.19 GFLOPS | Progress: (4/10) | 1.97 s
[Task 2/25] Current/Best: 18.87/ 19.19 GFLOPS | Progress: (8/10) | 3.13 s
[Task 2/25] Current/Best: 7.00/ 19.19 GFLOPS | Progress: (10/10) | 3.84 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 7.64/ 21.64 GFLOPS | Progress: (4/10) | 4.22 s
[Task 3/25] Current/Best: 9.26/ 21.64 GFLOPS | Progress: (8/10) | 6.61 s
[Task 3/25] Current/Best: 6.59/ 21.64 GFLOPS | Progress: (10/10) | 8.05 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 15.42/ 17.23 GFLOPS | Progress: (4/10) | 2.61 s
[Task 4/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (8/10) | 8.40 s
[Task 4/25] Current/Best: 16.89/ 19.95 GFLOPS | Progress: (10/10) | 9.19 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 6.72/ 13.85 GFLOPS | Progress: (4/10) | 2.98 s
[Task 5/25] Current/Best: 10.26/ 18.06 GFLOPS | Progress: (8/10) | 4.87 s
[Task 5/25] Current/Best: 15.64/ 18.06 GFLOPS | Progress: (10/10) | 5.67 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 8.90/ 16.16 GFLOPS | Progress: (4/10) | 3.73 s
[Task 6/25] Current/Best: 4.34/ 17.06 GFLOPS | Progress: (8/10) | 6.30 s
[Task 6/25] Current/Best: 9.98/ 21.50 GFLOPS | Progress: (10/10) | 7.11 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 11.12/ 14.10 GFLOPS | Progress: (4/10) | 3.75 s
[Task 7/25] Current/Best: 3.16/ 17.18 GFLOPS | Progress: (8/10) | 6.82 s
[Task 7/25] Current/Best: 10.78/ 17.18 GFLOPS | Progress: (10/10) | 8.00 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 13.81/ 13.81 GFLOPS | Progress: (4/10) | 7.24 s
[Task 8/25] Current/Best: 12.34/ 13.81 GFLOPS | Progress: (8/10) | 13.46 s
[Task 8/25] Current/Best: 5.14/ 13.81 GFLOPS | Progress: (10/10) | 18.80 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 15.14/ 15.14 GFLOPS | Progress: (4/10) | 5.24 s
[Task 9/25] Current/Best: 17.71/ 22.87 GFLOPS | Progress: (8/10) | 6.55 s
[Task 9/25] Current/Best: 17.87/ 22.87 GFLOPS | Progress: (10/10) | 7.29 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 12.87/ 12.87 GFLOPS | Progress: (4/10) | 3.52 s
[Task 10/25] Current/Best: 12.55/ 12.88 GFLOPS | Progress: (8/10) | 6.01 s
[Task 10/25] Current/Best: 12.25/ 12.88 GFLOPS | Progress: (10/10) | 6.86 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 9.65/ 18.54 GFLOPS | Progress: (4/10) | 3.05 s
[Task 11/25] Current/Best: 18.03/ 20.22 GFLOPS | Progress: (8/10) | 5.13 s
[Task 11/25] Current/Best: 16.29/ 20.22 GFLOPS | Progress: (10/10) | 5.97 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 10.32/ 16.41 GFLOPS | Progress: (4/10) | 6.29 s
[Task 12/25] Current/Best: 18.88/ 19.41 GFLOPS | Progress: (8/10) | 9.29 s
[Task 12/25] Current/Best: 10.35/ 19.41 GFLOPS | Progress: (10/10) | 11.24 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (4/10) | 2.70 s
[Task 13/25] Current/Best: 13.26/ 23.21 GFLOPS | Progress: (8/10) | 5.93 s
[Task 13/25] Current/Best: 12.82/ 23.21 GFLOPS | Progress: (10/10) | 7.52 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (4/10) | 6.21 s
[Task 14/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (8/10) | 11.74 s
[Task 14/25] Current/Best: 2.66/ 20.85 GFLOPS | Progress: (10/10) | 13.24 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 11.30/ 11.30 GFLOPS | Progress: (4/10) | 2.42 s
[Task 15/25] Current/Best: 12.77/ 12.77 GFLOPS | Progress: (8/10) | 7.96 s
[Task 15/25] Current/Best: 7.99/ 12.77 GFLOPS | Progress: (10/10) | 10.49 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 6.99/ 15.69 GFLOPS | Progress: (4/10) | 2.86 s
[Task 16/25] Current/Best: 10.33/ 20.86 GFLOPS | Progress: (8/10) | 5.12 s
[Task 16/25] Current/Best: 6.88/ 20.86 GFLOPS | Progress: (10/10) | 5.77 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 1.56/ 14.18 GFLOPS | Progress: (4/10) | 5.00 s
[Task 17/25] Current/Best: 3.11/ 20.91 GFLOPS | Progress: (8/10) | 7.19 s
[Task 17/25] Current/Best: 1.56/ 20.91 GFLOPS | Progress: (10/10) | 10.69 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 10.28/ 22.20 GFLOPS | Progress: (4/10) | 3.80 s
[Task 18/25] Current/Best: 22.07/ 22.20 GFLOPS | Progress: (8/10) | 7.60 s
[Task 18/25] Current/Best: 19.21/ 22.20 GFLOPS | Progress: (10/10) | 8.49 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (4/10) | 4.75 s
[Task 19/25] Current/Best: 10.33/ 20.98 GFLOPS | Progress: (8/10) | 9.95 s
[Task 19/25] Current/Best: 20.36/ 20.98 GFLOPS | Progress: (10/10) | 11.31 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 8.43/ 18.68 GFLOPS | Progress: (4/10) | 4.18 s
[Task 20/25] Current/Best: 8.82/ 18.68 GFLOPS | Progress: (8/10) | 11.95 s
[Task 20/25] Current/Best: 19.00/ 19.00 GFLOPS | Progress: (10/10) | 13.09 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 13.15/ 23.43 GFLOPS | Progress: (4/10) | 4.93 s
[Task 1/25] Current/Best: 6.43/ 23.43 GFLOPS | Progress: (8/10) | 9.01 s
[Task 1/25] Current/Best: 14.83/ 23.43 GFLOPS | Progress: (10/10) | 10.04 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 4.19/ 15.20 GFLOPS | Progress: (4/10) | 2.07 s
[Task 2/25] Current/Best: 21.06/ 21.06 GFLOPS | Progress: (8/10) | 3.22 s
[Task 2/25] Current/Best: 13.14/ 21.06 GFLOPS | Progress: (10/10) | 3.84 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 8.44/ 15.69 GFLOPS | Progress: (4/10) | 3.73 s
[Task 3/25] Current/Best: 24.09/ 24.37 GFLOPS | Progress: (8/10) | 5.44 s
[Task 3/25] Current/Best: 19.10/ 24.37 GFLOPS | Progress: (10/10) | 6.19 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 8.43/ 12.77 GFLOPS | Progress: (4/10) | 4.38 s
[Task 4/25] Current/Best: 5.03/ 18.40 GFLOPS | Progress: (8/10) | 8.82 s
[Task 4/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (10/10) | 10.71 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 5.80/ 16.18 GFLOPS | Progress: (4/10) | 2.98 s
[Task 5/25] Current/Best: 17.86/ 17.86 GFLOPS | Progress: (8/10) | 5.10 s
[Task 5/25] Current/Best: 17.48/ 17.86 GFLOPS | Progress: (10/10) | 5.82 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 15.06/ 15.49 GFLOPS | Progress: (4/10) | 3.70 s
[Task 6/25] Current/Best: 12.00/ 15.49 GFLOPS | Progress: (8/10) | 8.02 s
[Task 6/25] Current/Best: 5.99/ 23.22 GFLOPS | Progress: (10/10) | 9.06 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 11.04/ 18.45 GFLOPS | Progress: (4/10) | 2.82 s
[Task 7/25] Current/Best: 15.43/ 20.90 GFLOPS | Progress: (8/10) | 4.42 s
[Task 7/25] Current/Best: 9.26/ 20.90 GFLOPS | Progress: (10/10) | 5.56 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 10.36/ 10.36 GFLOPS | Progress: (4/10) | 4.21 s
[Task 8/25] Current/Best: 10.10/ 15.41 GFLOPS | Progress: (8/10) | 6.89 s
[Task 8/25] Current/Best: 18.08/ 18.08 GFLOPS | Progress: (10/10) | 7.71 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 8.52/ 16.92 GFLOPS | Progress: (4/10) | 6.65 s
[Task 9/25] Current/Best: 7.96/ 20.75 GFLOPS | Progress: (8/10) | 11.78 s
[Task 9/25] Current/Best: 10.00/ 20.75 GFLOPS | Progress: (10/10) | 13.15 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 13.48/ 18.47 GFLOPS | Progress: (4/10) | 2.61 s
[Task 10/25] Current/Best: 18.03/ 18.47 GFLOPS | Progress: (8/10) | 4.53 s
[Task 10/25] Current/Best: 22.03/ 22.03 GFLOPS | Progress: (10/10) | 5.07 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 10.72/ 21.43 GFLOPS | Progress: (4/10) | 2.93 s
[Task 11/25] Current/Best: 19.72/ 22.95 GFLOPS | Progress: (8/10) | 4.63 s
[Task 11/25] Current/Best: 23.01/ 23.01 GFLOPS | Progress: (10/10) | 5.89 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 15.98/ 15.98 GFLOPS | Progress: (4/10) | 2.74 s
[Task 12/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (8/10) | 4.24 s
[Task 12/25] Current/Best: 19.42/ 20.63 GFLOPS | Progress: (10/10) | 5.19 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 12.62/ 19.09 GFLOPS | Progress: (4/10) | 4.02 s
[Task 13/25] Current/Best: 10.27/ 19.79 GFLOPS | Progress: (8/10) | 7.36 s
[Task 13/25] Current/Best: 10.80/ 19.79 GFLOPS | Progress: (10/10) | 8.29 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 14.37/ 16.20 GFLOPS | Progress: (4/10) | 4.05 s
[Task 14/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (8/10) | 9.27 s
[Task 14/25] Current/Best: 3.61/ 17.77 GFLOPS | Progress: (10/10) | 10.63 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 14.00/ 19.09 GFLOPS | Progress: (4/10) | 2.58 s
[Task 15/25] Current/Best: 16.10/ 19.09 GFLOPS | Progress: (8/10) | 3.90 s
[Task 15/25] Current/Best: 16.90/ 19.09 GFLOPS | Progress: (10/10) | 4.67 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 11.78/ 19.88 GFLOPS | Progress: (4/10) | 3.58 s
[Task 16/25] Current/Best: 14.24/ 19.88 GFLOPS | Progress: (8/10) | 5.75 s
[Task 16/25] Current/Best: 14.78/ 19.88 GFLOPS | Progress: (10/10) | 6.46 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 4.71/ 18.50 GFLOPS | Progress: (4/10) | 4.94 s
[Task 17/25] Current/Best: 17.83/ 20.60 GFLOPS | Progress: (8/10) | 6.85 s
[Task 17/25] Current/Best: 14.98/ 20.60 GFLOPS | Progress: (10/10) | 8.06 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (4/10) | 2.94 s
[Task 18/25] Current/Best: 17.51/ 19.01 GFLOPS | Progress: (8/10) | 4.84 s
[Task 18/25] Current/Best: 10.36/ 19.27 GFLOPS | Progress: (10/10) | 5.62 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 16.78/ 16.78 GFLOPS | Progress: (4/10) | 3.70 s
[Task 19/25] Current/Best: 24.04/ 24.04 GFLOPS | Progress: (8/10) | 5.53 s
[Task 19/25] Current/Best: 22.92/ 24.04 GFLOPS | Progress: (10/10) | 7.15 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 4.59/ 18.68 GFLOPS | Progress: (4/10) | 2.97 s Done.
+
[Task 20/25] Current/Best: 8.03/ 18.68 GFLOPS | Progress: (8/10) | 4.96 s
[Task 20/25] Current/Best: 18.54/ 18.68 GFLOPS | Progress: (10/10) | 6.19 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 8.97/ 16.75 GFLOPS | Progress: (4/10) | 2.28 s
[Task 21/25] Current/Best: 10.16/ 22.75 GFLOPS | Progress: (8/10) | 4.63 s
[Task 21/25] Current/Best: 5.42/ 22.75 GFLOPS | Progress: (10/10) | 5.54 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 16.27/ 16.27 GFLOPS | Progress: (4/10) | 3.24 s
[Task 22/25] Current/Best: 9.06/ 16.27 GFLOPS | Progress: (8/10) | 4.78 s
[Task 22/25] Current/Best: 4.90/ 16.27 GFLOPS | Progress: (10/10) | 5.70 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 9.73/ 21.94 GFLOPS | Progress: (4/10) | 3.13 s
[Task 23/25] Current/Best: 1.55/ 21.94 GFLOPS | Progress: (8/10) | 7.46 s
[Task 23/25] Current/Best: 14.61/ 22.86 GFLOPS | Progress: (10/10) | 8.55 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 11.11/ 11.11 GFLOPS | Progress: (4/10) | 13.03 s
[Task 24/25] Current/Best: 9.40/ 11.11 GFLOPS | Progress: (8/10) | 20.46 s
[Task 24/25] Current/Best: 7.73/ 11.11 GFLOPS | Progress: (10/10) | 32.12 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 21/25] Current/Best: 2.73/ 16.26 GFLOPS | Progress: (4/10) | 5.01 s
[Task 21/25] Current/Best: 16.55/ 21.87 GFLOPS | Progress: (8/10) | 6.68 s
[Task 21/25] Current/Best: 12.72/ 21.87 GFLOPS | Progress: (10/10) | 7.73 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 17.91/ 17.97 GFLOPS | Progress: (4/10) | 2.93 s
[Task 22/25] Current/Best: 5.35/ 19.57 GFLOPS | Progress: (8/10) | 5.99 s
[Task 22/25] Current/Best: 6.98/ 19.57 GFLOPS | Progress: (10/10) | 6.73 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 8.11/ 19.02 GFLOPS | Progress: (4/10) | 3.62 s
[Task 23/25] Current/Best: 22.71/ 22.71 GFLOPS | Progress: (8/10) | 6.63 s
[Task 23/25] Current/Best: 9.80/ 22.71 GFLOPS | Progress: (10/10) | 8.41 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 3.72/ 8.60 GFLOPS | Progress: (4/10) | 6.60 s
[Task 24/25] Current/Best: 9.86/ 9.86 GFLOPS | Progress: (8/10) | 40.80 s
[Task 24/25] Current/Best: 2.59/ 9.86 GFLOPS | Progress: (10/10) | 46.31 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 3.00 GFLOPS | Progress: (4/10) | 33.29 s Done.
- Done.
-
[Task 25/25] Current/Best: 1.55/ 5.76 GFLOPS | Progress: (8/10) | 43.80 s
[Task 25/25] Current/Best: 9.27/ 9.27 GFLOPS | Progress: (10/10) | 389.25 s
+
[Task 25/25] Current/Best: 8.96/ 8.96 GFLOPS | Progress: (4/10) | 17.07 s
[Task 25/25] Current/Best: 9.79/ 10.33 GFLOPS | Progress: (8/10) | 18.63 s
[Task 25/25] Current/Best: 1.56/ 10.33 GFLOPS | Progress: (10/10) | 19.24 s
The output from this tuning process will look something like this:
@@ -595,7 +594,7 @@ 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='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
@@ -648,8 +647,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 458.3782529600012, 'median': 457.9627866500118, 'std': 1.3691634159363997}
- unoptimized: {'mean': 496.7789972299988, 'median': 496.78255254999897, 'std': 0.7418708641711039}
+ optimized: {'mean': 433.50518518999934, 'median': 433.5563567999998, 'std': 0.7088809294818195}
+ unoptimized: {'mean': 488.3565407600014, 'median': 488.1888957000001, 'std': 0.7026204955701438}
@@ -669,7 +668,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 13 minutes 59.777 seconds)
+ **Total running time of the script:** ( 6 minutes 43.662 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 ad204a351..be9341d1f 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.269e-07 secs/op
+ 1.248e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 26e46b546..52a4639c3 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -230,7 +230,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xde6d130)), stage(b, placeholder(b, 0xe39b250)), 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, 0xdba3de0)), stage(b, placeholder(b, 0x5433060)), 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 029827d8d..b1bc2fe58 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**16:42.845** total execution time for **tutorial** files:
+**09:29.676** total execution time for **tutorial** files:
-- **13:59.777**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **00:59.798**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:56.565**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:26.136**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:18.223**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.213**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.713**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.210**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.053**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.053**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.052**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.051**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **06:43.662**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:04.190**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:57.953**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:25.840**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:15.753**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:01.266**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.700**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.173**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.037**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.035**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.035**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.032**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 6b2f0a812..a32f26f3c 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -436,10 +436,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.687550000810006e-06 1.0
- naive 5.8384e-06 0.7594617269981764
- parallel 6.0158999999999994e-06 0.7825510077158689
- vector 2.45917e-05 3.1988995190156646
+ numpy 8.354089999329517e-06 1.0
+ naive 5.8574e-06 0.7011415965676816
+ parallel 6.0345e-06 0.7223407936093958
+ vector 2.4573600000000005e-05 2.9415052988383215
@@ -828,7 +828,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019735
+ Numpy running time: 0.018583
@@ -884,7 +884,7 @@ optimizations.
.. code-block:: none
- none: 3.299927
+ none: 3.196138
@@ -982,7 +982,7 @@ schedule.
.. code-block:: none
- blocking: 0.307180
+ blocking: 0.298252
@@ -1073,7 +1073,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.346809
+ vectorization: 0.333737
@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], []),
@@ -1144,7 +1144,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118853
+ loop permutation: 0.111516
@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], []),
@@ -1240,7 +1240,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.110135
+ array packing: 0.107850
@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], []),
@@ -1330,7 +1330,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110607
+ block caching: 0.110459
@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], []),
@@ -1413,7 +1413,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.142828
+ parallelization: 0.143365
@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.
.. code-block:: none
Operator Timing Performance
- none 3.2999269565000007 1.0
- blocking 0.3071802152 0.09308697412072549
- vectorization 0.34680917899999997 0.10509601684269883
- loop permutation 0.1188533219 0.03601695536499369
- array packing 0.1101353187 0.03337507773711838
- block caching 0.1106073233 0.03351811260007809
- parallelization 0.1428280522 0.04328218596434862
+ none 3.1961378924000003 1.0
+ blocking 0.2982516952 0.09331627897194414
+ vectorization 0.33373664290000005 0.10441872476578133
+ loop permutation 0.1115159348 0.03489083968034369
+ array packing 0.1078503934 0.03374397383055787
+ block caching 0.11045918210000001 0.03456020541624864
+ parallelization 0.14336543699999998 0.044855835957799045
diff --git a/docs/commit_hash b/docs/commit_hash
index 892894028..337fd7cf8 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-fcdf4636d866fefbf3e2a55daa614565ce97203a
+c2744704bec3cc914fa96dc4f4c9b0ccfaa8ace4
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 6176e8071..a00ae27cd 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -400,7 +400,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb1ef4cfb-7e93-4c74-8d67-82a960906f6d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip795bd19e-2151-46c5-94a6-56116b9f665b 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_onnx.html b/docs/how_to/compile_models/from_onnx.html
index 2815c4848..2890ebb2d 100644
--- a/docs/how_to/compile_models/from_onnx.html
+++ b/docs/how_to/compile_models/from_onnx.html
@@ -452,6 +452,13 @@ bicubic algorithm. The image is then recombined and converted back to <cite>RGB<
</pre></div>
</div>
<img alt="../../_images/sphx_glr_from_onnx_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_onnx_001.png" />
+<p class="sphx-glr-script-out">Out:</p>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/gallery/how_to/compile_models/from_onnx.py:114: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
+ out_cb = img_cb.resize(out_y.size, Image.BICUBIC)
+/workspace/gallery/how_to/compile_models/from_onnx.py:115: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
+ out_cr = img_cr.resize(out_y.size, Image.BICUBIC)
+</pre></div>
+</div>
</div>
<div class="section" id="notes">
<h2>Notes<a class="headerlink" href="#notes" title="Permalink to this headline">¶</a></h2>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 1280bebec..427ee89b3 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -359,6 +359,21 @@ A quick solution is</p>
<span class="kn">from</span> <span class="nn">tvm.contrib.download</span> <span class="k">import</span> <span class="n">download_testdata</span>
</pre></div>
</div>
+<p class="sphx-glr-script-out">Out:</p>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:36: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.NEAREST or Dither.NONE instead.
+ 'nearest': Image.NEAREST,
+/usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:37: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
+ 'bilinear': Image.BILINEAR,
+/usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:38: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
+ 'bicubic': Image.BICUBIC,
+/usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:39: DeprecationWarning: BOX is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BOX instead.
+ 'box': Image.BOX,
+/usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:40: DeprecationWarning: LANCZOS is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.LANCZOS instead.
+ 'lanczos': Image.LANCZOS,
+/usr/local/lib/python3.7/dist-packages/paddle/vision/transforms/functional_pil.py:41: DeprecationWarning: HAMMING is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.HAMMING instead.
+ 'hamming': Image.HAMMING
+</pre></div>
+</div>
<div class="section" id="load-pretrained-resnet50-model">
<h2>Load pretrained ResNet50 model<a class="headerlink" href="#load-pretrained-resnet50-model" title="Permalink to this headline">¶</a></h2>
<p>We load a pretrained ResNet50 provided by PaddlePaddle.</p>
@@ -448,7 +463,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.476 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.747 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.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_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 26ec06e7c..ddbec8775 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -386,9 +386,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 17%|#6 | 7.58M/44.7M [00:00<00:00, 79.5MB/s]
- 59%|#####9 | 26.5M/44.7M [00:00<00:00, 149MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 159MB/s]
+ 26%|##5 | 11.5M/44.7M [00:00<00:00, 121MB/s]
+ 67%|######6 | 29.7M/44.7M [00:00<00:00, 162MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 166MB/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 874297e88..8ff431212 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -606,7 +606,7 @@ 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 1.350 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.138 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download 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 35c8c2f21..515e85d0f 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,17 +300,17 @@
<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>04:48.458</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>04:47.919</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:05.476</strong>: <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></li>
-<li><p><strong>01:01.350</strong>: <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></li>
-<li><p><strong>00:56.199</strong>: <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></li>
-<li><p><strong>00:25.924</strong>: <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></li>
-<li><p><strong>00:21.935</strong>: <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></li>
-<li><p><strong>00:21.349</strong>: <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></li>
-<li><p><strong>00:19.504</strong>: <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></li>
-<li><p><strong>00:14.059</strong>: <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></li>
-<li><p><strong>00:02.663</strong>: <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></li>
+<li><p><strong>01:04.747</strong>: <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></li>
+<li><p><strong>01:00.138</strong>: <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></li>
+<li><p><strong>00:56.256</strong>: <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></li>
+<li><p><strong>00:27.554</strong>: <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></li>
+<li><p><strong>00:21.088</strong>: <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></li>
+<li><p><strong>00:21.056</strong>: <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></li>
+<li><p><strong>00:19.118</strong>: <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></li>
+<li><p><strong>00:15.492</strong>: <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></li>
+<li><p><strong>00:02.469</strong>: <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></li>
</ul>
</div>
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 10aeb086a..7132b60ff 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0546 16.0586 16.3876 15.6943 0.1770
+ 15.8478 15.7898 16.1872 15.7288 0.1350
</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 ab218b57c..e39211972 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,34 +409,17 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 1%|1 | 2.38M/170M [00:00<00:07, 23.5MB/s]
- 3%|3 | 5.42M/170M [00:00<00:06, 26.2MB/s]
- 5%|4 | 8.09M/170M [00:00<00:06, 26.7MB/s]
- 6%|6 | 10.6M/170M [00:00<00:06, 24.6MB/s]
- 10%|9 | 16.4M/170M [00:00<00:04, 36.4MB/s]
- 12%|#1 | 20.1M/170M [00:00<00:04, 35.8MB/s]
- 16%|#6 | 27.7M/170M [00:00<00:03, 49.4MB/s]
- 20%|#9 | 33.4M/170M [00:00<00:02, 52.6MB/s]
- 23%|##2 | 38.7M/170M [00:00<00:02, 53.2MB/s]
- 27%|##7 | 46.5M/170M [00:01<00:02, 61.8MB/s]
- 33%|###2 | 55.3M/170M [00:01<00:01, 70.9MB/s]
- 37%|###6 | 62.1M/170M [00:01<00:01, 61.7MB/s]
- 42%|####1 | 71.3M/170M [00:01<00:01, 71.2MB/s]
- 46%|####6 | 78.4M/170M [00:01<00:01, 71.1MB/s]
- 50%|##### | 85.4M/170M [00:01<00:01, 58.0MB/s]
- 54%|#####3 | 91.4M/170M [00:01<00:01, 52.2MB/s]
- 58%|#####8 | 98.9M/170M [00:01<00:01, 58.3MB/s]
- 63%|######2 | 107M/170M [00:02<00:01, 63.9MB/s]
- 67%|######7 | 114M/170M [00:02<00:00, 66.7MB/s]
- 71%|#######1 | 121M/170M [00:02<00:00, 69.4MB/s]
- 77%|#######6 | 130M/170M [00:02<00:00, 75.1MB/s]
- 81%|######## | 137M/170M [00:02<00:00, 66.5MB/s]
- 85%|########5 | 145M/170M [00:02<00:00, 70.3MB/s]
- 90%|########9 | 152M/170M [00:02<00:00, 60.6MB/s]
- 93%|#########3| 158M/170M [00:02<00:00, 54.2MB/s]
- 96%|#########6| 164M/170M [00:03<00:00, 52.7MB/s]
-100%|#########9| 170M/170M [00:03<00:00, 55.0MB/s]
-100%|##########| 170M/170M [00:03<00:00, 56.6MB/s]
+ 6%|6 | 10.4M/170M [00:00<00:01, 109MB/s]
+ 15%|#4 | 25.0M/170M [00:00<00:01, 135MB/s]
+ 25%|##4 | 42.1M/170M [00:00<00:00, 155MB/s]
+ 35%|###4 | 59.4M/170M [00:00<00:00, 165MB/s]
+ 45%|####5 | 76.6M/170M [00:00<00:00, 170MB/s]
+ 55%|#####5 | 94.0M/170M [00:00<00:00, 175MB/s]
+ 66%|######5 | 111M/170M [00:00<00:00, 177MB/s]
+ 76%|#######5 | 129M/170M [00:00<00:00, 178MB/s]
+ 86%|########5 | 146M/170M [00:00<00:00, 179MB/s]
+ 96%|#########5| 163M/170M [00:01<00:00, 179MB/s]
+100%|##########| 170M/170M [00:01<00:00, 171MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: 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)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: 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').
@@ -529,7 +512,7 @@ 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 10.430 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 1.658 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download 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 a70746495..090855bc9 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,9 +450,10 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 38%|###7 | 5.14M/13.6M [00:00<00:00, 53.8MB/s]
-100%|#########9| 13.5M/13.6M [00:00<00:00, 73.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 70.8MB/s]
+ 31%|###1 | 4.21M/13.6M [00:00<00:00, 44.1MB/s]
+ 62%|######2 | 8.41M/13.6M [00:00<00:00, 39.1MB/s]
+ 97%|#########7| 13.2M/13.6M [00:00<00:00, 43.6MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 42.8MB/s]
</pre></div>
</div>
</div>
@@ -541,7 +542,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<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)
- 90.2897 90.1839 93.8210 90.0559 0.4222
+ 90.3214 90.1819 101.8479 89.8892 1.1982
</pre></div>
</div>
<div class="admonition note">
@@ -580,7 +581,7 @@ 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 5.783 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.963 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download 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 243595cd1..0ee2056fa 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<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)
- 120.1680 120.1239 123.2265 119.4900 0.4609
+ 119.2355 119.2110 120.7470 118.3210 0.4406
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ 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> ( 1 minutes 58.866 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 1.184 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download 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 6da8d6b6d..ca238498f 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 45.802 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.381 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download 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 92f5d9dd5..4ad73234b 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,23 +415,25 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5778/132723 [00:00<00:02, 57776.06KB/s]
- 10%|# | 13486/132723 [00:00<00:01, 69122.61KB/s]
- 16%|#5 | 21213/132723 [00:00<00:01, 72839.43KB/s]
- 22%|##1 | 28897/132723 [00:00<00:01, 74382.39KB/s]
- 27%|##7 | 36496/132723 [00:00<00:01, 74959.67KB/s]
- 34%|###3 | 44482/132723 [00:00<00:01, 76622.52KB/s]
- 40%|###9 | 52523/132723 [00:00<00:01, 77853.30KB/s]
- 46%|####5 | 60640/132723 [00:00<00:00, 78904.86KB/s]
- 52%|#####1 | 68714/132723 [00:00<00:00, 79476.52KB/s]
- 58%|#####7 | 76849/132723 [00:01<00:00, 80053.20KB/s]
- 64%|######4 | 84958/132723 [00:01<00:00, 80368.51KB/s]
- 70%|####### | 93122/132723 [00:01<00:00, 80753.42KB/s]
- 76%|#######6 | 101269/132723 [00:01<00:00, 80968.11KB/s]
- 82%|########2 | 109416/132723 [00:01<00:00, 81117.20KB/s]
- 89%|########8 | 117602/132723 [00:01<00:00, 81338.66KB/s]
- 95%|#########4| 125743/132723 [00:01<00:00, 81357.76KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 78708.31KB/s]
+ 4%|3 | 5009/132723 [00:00<00:02, 50077.15KB/s]
+ 9%|9 | 12105/132723 [00:00<00:01, 62354.76KB/s]
+ 15%|#4 | 19816/132723 [00:00<00:01, 69087.52KB/s]
+ 21%|## | 27624/132723 [00:00<00:01, 72634.39KB/s]
+ 26%|##6 | 34888/132723 [00:00<00:01, 59341.22KB/s]
+ 31%|###1 | 41148/132723 [00:00<00:01, 51108.96KB/s]
+ 36%|###5 | 47389/132723 [00:00<00:01, 54090.97KB/s]
+ 40%|#### | 53102/132723 [00:00<00:01, 50008.92KB/s]
+ 44%|####3 | 58335/132723 [00:01<00:01, 49509.75KB/s]
+ 50%|####9 | 66063/132723 [00:01<00:01, 56960.31KB/s]
+ 56%|#####5 | 73779/132723 [00:01<00:00, 62557.99KB/s]
+ 61%|######1 | 81613/132723 [00:01<00:00, 67031.93KB/s]
+ 67%|######7 | 89470/132723 [00:01<00:00, 70353.65KB/s]
+ 73%|#######3 | 97278/132723 [00:01<00:00, 72605.57KB/s]
+ 79%|#######9 | 105042/132723 [00:01<00:00, 74085.33KB/s]
+ 85%|########5 | 112865/132723 [00:01<00:00, 75308.78KB/s]
+ 91%|######### | 120717/132723 [00:01<00:00, 76237.20KB/s]
+ 97%|#########6| 128544/132723 [00:01<00:00, 76841.47KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 65703.53KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -471,7 +473,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.727 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.711 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download 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 703fdd8f9..5ce65602f 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>11:14.502</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:42.517</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:10.430</strong>: <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></li>
-<li><p><strong>02:23.727</strong>: <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></li>
-<li><p><strong>01:58.866</strong>: <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></li>
-<li><p><strong>01:45.802</strong>: <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></li>
-<li><p><strong>01:05.783</strong>: <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></li>
-<li><p><strong>00:27.853</strong>: <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></li>
-<li><p><strong>00:21.846</strong>: <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></li>
-<li><p><strong>00:00.194</strong>: <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></li>
+<li><p><strong>03:01.658</strong>: <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></li>
+<li><p><strong>02:20.711</strong>: <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></li>
+<li><p><strong>02:01.184</strong>: <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></li>
+<li><p><strong>01:25.381</strong>: <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></li>
+<li><p><strong>01:03.963</strong>: <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></li>
+<li><p><strong>00:27.654</strong>: <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></li>
+<li><p><strong>00:21.784</strong>: <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></li>
+<li><p><strong>00:00.184</strong>: <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></li>
</ul>
</div>
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 ef66a6910..0e07879c4 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip18d6b82f-2221-4365-980d-325aec9223b1 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.zip945f3aed-ce8d-4ab0-aed1-a30043a26a46 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 6ef6a1d36..dccb40348 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<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>00:38.410</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.362</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.887</strong>: <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></li>
-<li><p><strong>00:02.255</strong>: <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></li>
-<li><p><strong>00:01.065</strong>: <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></li>
-<li><p><strong>00:00.203</strong>: <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></li>
+<li><p><strong>00:33.959</strong>: <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></li>
+<li><p><strong>00:02.195</strong>: <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></li>
+<li><p><strong>00:01.018</strong>: <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></li>
+<li><p><strong>00:00.191</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 9a13b1ad5..134cb8b1b 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5974us [5974us] (45.52%; 45.52%)
-FoldScaleAxis: 7150us [2us] (54.48%; 54.48%)
- FoldConstant: 7147us [1461us] (54.46%; 99.97%)
- InferType: 5686us [5686us] (43.33%; 79.55%)
+InferType: 5933us [5933us] (45.43%; 45.43%)
+FoldScaleAxis: 7128us [2us] (54.57%; 54.57%)
+ FoldConstant: 7126us [1487us] (54.55%; 99.97%)
+ InferType: 5638us [5638us] (43.17%; 79.13%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5743us [5743us] (44.57%; 44.57%)
-FoldScaleAxis: 7142us [2us] (55.43%; 55.43%)
- FoldConstant: 7139us [1504us] (55.41%; 99.97%)
- InferType: 5635us [5635us] (43.74%; 78.93%)
+InferType: 5713us [5713us] (44.30%; 44.30%)
+FoldScaleAxis: 7183us [2us] (55.70%; 55.70%)
+ FoldConstant: 7180us [1517us] (55.68%; 99.97%)
+ InferType: 5664us [5664us] (43.92%; 78.88%)
</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 3f5bb7b7f..2b3312f0d 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 51.561264 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.672973 ms
</pre></div>
</div>
<div class="sphx-glr-footer class 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 a6835e4cc..2b5e782ae 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -876,7 +876,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.854424 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.197852 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 18809d542..51291542c 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018808
-Baseline: 3.260891
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018419
+Baseline: 3.195817
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -493,7 +493,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.311549
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.297370
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -561,7 +561,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.341674
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333479
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -623,7 +623,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116943
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115630
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -707,7 +707,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110352
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110539
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -794,7 +794,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111289
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110639
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -885,7 +885,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145131
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144140
</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 a72c2c869..9b71d679f 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.846</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.203</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.196</strong>: <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></li>
-<li><p><strong>00:01.425</strong>: <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></li>
-<li><p><strong>00:01.225</strong>: <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></li>
+<li><p><strong>00:31.573</strong>: <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></li>
+<li><p><strong>00:01.427</strong>: <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></li>
+<li><p><strong>00:01.203</strong>: <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></li>
</ul>
</div>
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 739605fa0..02147badb 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<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>04:56.081</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>04:53.263</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:21.190</strong>: <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></li>
-<li><p><strong>01:20.183</strong>: <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></li>
-<li><p><strong>00:40.548</strong>: <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></li>
-<li><p><strong>00:16.893</strong>: <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></li>
-<li><p><strong>00:08.793</strong>: <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></li>
-<li><p><strong>00:08.475</strong>: <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></li>
+<li><p><strong>02:20.559</strong>: <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></li>
+<li><p><strong>01:19.357</strong>: <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></li>
+<li><p><strong>00:39.826</strong>: <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></li>
+<li><p><strong>00:16.849</strong>: <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></li>
+<li><p><strong>00:08.454</strong>: <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></li>
+<li><p><strong>00:08.218</strong>: <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></li>
</ul>
</div>
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 c3d4f98a9..dabedaf45 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
@@ -469,11 +469,11 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), 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" = 224 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -481,156 +481,736 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 256) {
- let cse_var_2: int32 = (rc.outer.outer*98)
- let cse_var_1: int32 = (rc.outer.outer*18)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 31), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ for (rc.outer.outer: int32, 0, 16) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 32), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(th [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 64), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(th [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 96), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(th [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 128), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(t [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 160), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 192), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 256), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod( [...]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 7), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 14), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 28), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 35), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 49), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 56), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 70), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 77), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 96)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 32), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + rx.outer.outer) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_2 < 160), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 32) + 91), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + rx.outer.outer)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 75)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 76)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 78)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 79)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 80)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 633)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 634)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 635)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 636)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 696)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 697)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 698)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 699)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 759)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 760)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 761)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 762)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 885)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 886)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 887)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 888)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 948)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 949)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 950)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 951)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1009)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1010)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1011)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1012)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1013)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1014)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1016)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1017)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1018)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1019)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1020)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1021)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1023)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1024)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1025)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1026)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1027)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1028)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1079)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1080)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1081)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1082)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1083)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1084)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1086)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1087)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1088)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1089)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1090)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1091)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1210)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1212)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1213)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1214)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1273)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1275)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1276)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1277)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1278)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1399)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1401)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1402)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1403)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1404)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1462)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1464)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1465)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1466)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1467)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1525)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1527)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1528)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1529)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1530)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1655)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1656)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1714)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1716)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1717)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1718)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1719)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1720)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1721)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1777)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1779)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1780)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1781)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1782)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1783)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1784)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1840)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1842)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1843)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1844)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1845)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1846)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1847)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1907)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1908)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1966)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1968)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1969)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1970)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1971)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + 95)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 2) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
- 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 + 112)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 2) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*18) + 17)]))
}
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -668,7 +1248,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.318 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.410 ms
</pre></div>
</div>
</div>
@@ -700,34 +1280,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
conv2d_nchw_ff_o_o_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=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_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
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_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_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_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
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=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
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=7)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_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_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)
@@ -747,12 +1327,12 @@ 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=56)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
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", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -772,10 +1352,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[162];
- __shared__ float kernel_shared[144];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -783,148 +1363,711 @@ extern "C" __global__ void __launch_bounds__(56) default_function_kern
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((int)threadIdx.x) < 41) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 129024)];
+ if (((int)threadIdx.x) < 160) {
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + rx_outer_outer)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 75)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 76)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 77)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 78)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 79)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 80)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 633)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 634)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 635)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 636)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 637)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 696)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 697)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 698)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 699)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 700)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 759)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 760)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 761)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 762)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 763)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 885)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 886)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 887)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 888)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 889)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 948)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 949)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 950)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 951)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 952)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1011)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1012)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1013)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1014)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1016)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1017)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1018)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1019)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1020)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1021)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1023)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1024)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1025)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1026)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1027)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1028)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1079)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1080)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1081)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1082)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1083)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1084)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1086)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1087)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1088)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1089)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1090)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1091)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1210)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1212)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1213)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1214)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1273)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1275)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1276)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1277)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1278)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1399)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1401)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1402)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1403)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1404)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1462)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1464)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1465)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1466)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1467)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1525)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1527)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1528)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1529)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1530)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1655)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1656)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1714)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1716)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1717)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1718)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1719)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1720)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1721)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1777)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1779)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1780)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1781)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1782)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1783)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1784)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1840)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1842)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1843)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1844)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1845)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1846)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1847)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1907)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1908)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1966)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1968)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1969)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1970)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1971)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 18) + 17)]));
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
</pre></div>
@@ -962,7 +2105,7 @@ 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> ( 2 minutes 21.190 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.559 seconds)</p>
<div class="sphx-glr-footer class 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 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 26bf40d31..ab0d27b9e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ 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)
- 9.9008 9.9027 9.9199 9.8797 0.0165
+ 9.7098 9.7199 9.7400 9.6697 0.0296
</pre></div>
</div>
</div>
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 eeae48bfa..9a3f564fe 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ 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)
- 770.2555 771.6021 776.6457 762.5187 5.8454
+ 759.2196 758.9126 765.6314 753.1150 5.1144
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ 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 20.183 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.357 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download 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 5fab381f6..e35ccab7b 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -602,75 +602,214 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
- compute_4[(cse_var_1 + 1)] = 0f32
- compute_4[(cse_var_1 + 2)] = 0f32
- compute_4[(cse_var_1 + 3)] = 0f32
- compute_4[(cse_var_1 + 4)] = 0f32
- compute_4[(cse_var_1 + 5)] = 0f32
- compute_4[(cse_var_1 + 6)] = 0f32
- compute_4[(cse_var_1 + 7)] = 0f32
- compute_4[(cse_var_1 + 8)] = 0f32
- compute_4[(cse_var_1 + 9)] = 0f32
- compute_4[(cse_var_1 + 10)] = 0f32
- compute_4[(cse_var_1 + 11)] = 0f32
- compute_4[(cse_var_1 + 12)] = 0f32
- compute_4[(cse_var_1 + 13)] = 0f32
- compute_4[(cse_var_1 + 14)] = 0f32
- compute_4[(cse_var_1 + 15)] = 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, 8) {
- 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*2048) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 1)
- let cse_var_16: int32 = (cse_var_18 + 11)
- let cse_var_15: int32 = (cse_var_18 + 12)
- let cse_var_14: int32 = (cse_var_18 + 13)
- let cse_var_13: int32 = (cse_var_18 + 14)
- let cse_var_12: int32 = (cse_var_18 + 15)
- let cse_var_11: int32 = (cse_var_18 + 2)
- let cse_var_10: int32 = (cse_var_18 + 3)
- let cse_var_9: int32 = (cse_var_18 + 4)
- let cse_var_8: int32 = (cse_var_18 + 5)
- let cse_var_7: int32 = (cse_var_18 + 6)
- let cse_var_6: int32 = (cse_var_18 + 7)
- let cse_var_5: int32 = (cse_var_18 + 8)
- let cse_var_4: int32 = (cse_var_18 + 9)
- let cse_var_3: int32 = (cse_var_18 + 10)
+ let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ compute_4[(cse_var_1 + 32)] = 0f32
+ compute_4[(cse_var_1 + 33)] = 0f32
+ compute_4[(cse_var_1 + 34)] = 0f32
+ compute_4[(cse_var_1 + 35)] = 0f32
+ compute_4[(cse_var_1 + 36)] = 0f32
+ compute_4[(cse_var_1 + 37)] = 0f32
+ compute_4[(cse_var_1 + 38)] = 0f32
+ compute_4[(cse_var_1 + 39)] = 0f32
+ compute_4[(cse_var_1 + 40)] = 0f32
+ compute_4[(cse_var_1 + 41)] = 0f32
+ compute_4[(cse_var_1 + 42)] = 0f32
+ compute_4[(cse_var_1 + 43)] = 0f32
+ compute_4[(cse_var_1 + 44)] = 0f32
+ compute_4[(cse_var_1 + 45)] = 0f32
+ compute_4[(cse_var_1 + 46)] = 0f32
+ compute_4[(cse_var_1 + 47)] = 0f32
+ compute_4[(cse_var_1 + 64)] = 0f32
+ compute_4[(cse_var_1 + 65)] = 0f32
+ compute_4[(cse_var_1 + 66)] = 0f32
+ compute_4[(cse_var_1 + 67)] = 0f32
+ compute_4[(cse_var_1 + 68)] = 0f32
+ compute_4[(cse_var_1 + 69)] = 0f32
+ compute_4[(cse_var_1 + 70)] = 0f32
+ compute_4[(cse_var_1 + 71)] = 0f32
+ compute_4[(cse_var_1 + 72)] = 0f32
+ compute_4[(cse_var_1 + 73)] = 0f32
+ compute_4[(cse_var_1 + 74)] = 0f32
+ compute_4[(cse_var_1 + 75)] = 0f32
+ compute_4[(cse_var_1 + 76)] = 0f32
+ compute_4[(cse_var_1 + 77)] = 0f32
+ compute_4[(cse_var_1 + 78)] = 0f32
+ compute_4[(cse_var_1 + 79)] = 0f32
+ compute_4[(cse_var_1 + 96)] = 0f32
+ compute_4[(cse_var_1 + 97)] = 0f32
+ compute_4[(cse_var_1 + 98)] = 0f32
+ compute_4[(cse_var_1 + 99)] = 0f32
+ compute_4[(cse_var_1 + 100)] = 0f32
+ compute_4[(cse_var_1 + 101)] = 0f32
+ compute_4[(cse_var_1 + 102)] = 0f32
+ compute_4[(cse_var_1 + 103)] = 0f32
+ compute_4[(cse_var_1 + 104)] = 0f32
+ compute_4[(cse_var_1 + 105)] = 0f32
+ compute_4[(cse_var_1 + 106)] = 0f32
+ compute_4[(cse_var_1 + 107)] = 0f32
+ compute_4[(cse_var_1 + 108)] = 0f32
+ compute_4[(cse_var_1 + 109)] = 0f32
+ compute_4[(cse_var_1 + 110)] = 0f32
+ compute_4[(cse_var_1 + 111)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ let cse_var_67: int32 = (cse_var_1 + 41)
+ let cse_var_66: int32 = (cse_var_1 + 40)
+ let cse_var_65: int32 = (cse_var_1 + 4)
+ let cse_var_64: int32 = (cse_var_1 + 39)
+ let cse_var_63: int32 = (cse_var_1 + 38)
+ let cse_var_62: int32 = (cse_var_1 + 37)
+ let cse_var_61: int32 = (cse_var_1 + 36)
+ let cse_var_60: int32 = (cse_var_1 + 35)
+ let cse_var_59: int32 = (cse_var_1 + 34)
+ let cse_var_58: int32 = (cse_var_1 + 33)
+ let cse_var_57: int32 = (cse_var_1 + 32)
+ let cse_var_56: int32 = (cse_var_1 + 3)
+ let cse_var_55: int32 = (cse_var_1 + 2)
+ let cse_var_54: int32 = (cse_var_1 + 15)
+ let cse_var_53: int32 = (cse_var_1 + 14)
+ let cse_var_52: int32 = (cse_var_1 + 1)
+ let cse_var_51: int32 = (cse_var_1 + 12)
+ let cse_var_50: int32 = (cse_var_1 + 111)
+ let cse_var_49: int32 = (cse_var_1 + 110)
+ let cse_var_48: int32 = (cse_var_1 + 11)
+ let cse_var_47: int32 = (cse_var_1 + 109)
+ let cse_var_46: int32 = (cse_var_1 + 108)
+ let cse_var_45: int32 = (cse_var_1 + 107)
+ let cse_var_44: int32 = (cse_var_1 + 106)
+ let cse_var_43: int32 = (cse_var_1 + 105)
+ let cse_var_42: int32 = (cse_var_1 + 104)
+ let cse_var_41: int32 = (cse_var_1 + 103)
+ let cse_var_40: int32 = (cse_var_1 + 102)
+ let cse_var_39: int32 = (cse_var_1 + 101)
+ let cse_var_38: int32 = (cse_var_1 + 100)
+ let cse_var_37: int32 = (cse_var_1 + 10)
+ let cse_var_36: int32 = (cse_var_1 + 13)
+ let cse_var_35: int32 = (i.outer.inner*1024)
+ let cse_var_34: int32 = (elem_idx*16)
+ let cse_var_33: int32 = (cse_var_1 + 99)
+ let cse_var_32: int32 = (cse_var_1 + 98)
+ let cse_var_31: int32 = (cse_var_1 + 97)
+ let cse_var_30: int32 = (cse_var_1 + 96)
+ let cse_var_29: int32 = (cse_var_1 + 9)
+ let cse_var_28: int32 = (cse_var_1 + 8)
+ let cse_var_27: int32 = (cse_var_1 + 79)
+ let cse_var_26: int32 = (cse_var_1 + 78)
+ let cse_var_25: int32 = (cse_var_1 + 77)
+ let cse_var_24: int32 = (cse_var_1 + 76)
+ let cse_var_23: int32 = (cse_var_1 + 75)
+ let cse_var_22: int32 = (cse_var_1 + 74)
+ let cse_var_21: int32 = (cse_var_1 + 73)
+ let cse_var_20: int32 = (cse_var_1 + 42)
+ let cse_var_19: int32 = (cse_var_1 + 43)
+ let cse_var_18: int32 = (cse_var_1 + 44)
+ let cse_var_17: int32 = (cse_var_1 + 45)
+ let cse_var_16: int32 = (cse_var_1 + 46)
+ let cse_var_15: int32 = (cse_var_1 + 47)
+ let cse_var_14: int32 = (cse_var_1 + 5)
+ let cse_var_13: int32 = (cse_var_1 + 6)
+ let cse_var_12: int32 = (cse_var_1 + 72)
+ let cse_var_11: int32 = (cse_var_1 + 65)
+ let cse_var_10: int32 = (cse_var_1 + 66)
+ let cse_var_9: int32 = (cse_var_1 + 67)
+ let cse_var_8: int32 = (cse_var_1 + 68)
+ let cse_var_7: int32 = (cse_var_1 + 69)
+ let cse_var_6: int32 = (cse_var_1 + 7)
+ let cse_var_5: int32 = (cse_var_1 + 70)
+ let cse_var_4: int32 = (cse_var_1 + 71)
+ let cse_var_3: int32 = (cse_var_1 + 64)
{
- compute_4[cse_var_18] = (compute_4[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_4[cse_var_17] = (compute_4[cse_var_17] + (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_4[cse_var_11] = (compute_4[cse_var_11] + (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_4[cse_var_10] = (compute_4[cse_var_10] + (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_4[cse_var_9] = (compute_4[cse_var_9] + (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_4[cse_var_8] = (compute_4[cse_var_8] + (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_4[cse_var_7] = (compute_4[cse_var_7] + (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_4[cse_var_6] = (compute_4[cse_var_6] + (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_4[cse_var_5] = (compute_4[cse_var_5] + (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_4[cse_var_4] = (compute_4[cse_var_4] + (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_4[cse_var_3] = (compute_4[cse_var_3] + (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_4[cse_var_16] = (compute_4[cse_var_16] + (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_4[cse_var_15] = (compute_4[cse_var_15] + (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_4[cse_var_14] = (compute_4[cse_var_14] + (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_4[cse_var_13] = (compute_4[cse_var_13] + (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_4[cse_var_12] = (compute_4[cse_var_12] + (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)))
+ compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[(cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_34)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 1)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 2)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 3)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 4)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 5)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 6)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 7)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 8)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 9)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 10)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 11)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 12)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 13)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 14)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_34) + 15)]*max(placeholder[((cse_var_35 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 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_4[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ let cse_var_68: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_68, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -709,7 +848,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.856 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.026 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 c37f8a082..8470a2c68 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:44.076</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.101</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.226</strong>: <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></li>
-<li><p><strong>00:00.222</strong>: <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></li>
-<li><p><strong>00:00.210</strong>: <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></li>
-<li><p><strong>00:00.209</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
-<li><p><strong>00:00.209</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:43.285</strong>: <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></li>
+<li><p><strong>00:00.216</strong>: <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></li>
+<li><p><strong>00:00.202</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:00.200</strong>: <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></li>
+<li><p><strong>00:00.199</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
</ul>
</div>
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 05f141449..8c4278c5d 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.29/42.29 result: MeasureResult(costs=(0.005474721105263158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5929961204528809, timestamp=1649040668.6649668) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 6 GFLOPS: 103.38/103.38 result: MeasureResult(costs=(0.0022393124791666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5896687507629395, timestamp=1649098570.4953766) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.29 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/103.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fabcb57bfa2
+ 12: 0x00007f5adc41dfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 144.34/144.34 result: MeasureResult(costs=(0.0016038595799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4119071960449219, timestamp=1649040694.311562) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 145.02/145.02 result: MeasureResult(costs=(0.00159632587,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4061989784240723, timestamp=1649098596.76297) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.002023
+Time cost of this operator: 0.002075
</pre></div>
</div>
<div class="sphx-glr-footer class 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 295f274f7..ce2ec5afc 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ 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
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.2 98.749 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.963 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.289 (1, 1, 10, 10, 3) 1 1
-Total_time - 319.194 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.7 98.749 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.957 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.294 (1, 1, 10, 10, 3) 1 1
+Total_time - 313.623 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ 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
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 197.4 98.673 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.753 0.876 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.45 (1, 3, 10, 10, 1) 1 1
-Total_time - 200.054 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 124.2 97.839 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.414 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.949 0.748 (1, 1, 10, 10, 3) 1 1
+Total_time - 126.944 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class 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/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 5742e0718..6579013c5 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:44.498</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:43.889</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:40.422</strong>: <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></li>
-<li><p><strong>00:03.488</strong>: <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></li>
-<li><p><strong>00:00.197</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
-<li><p><strong>00:00.195</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
-<li><p><strong>00:00.195</strong>: <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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:39.919</strong>: <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></li>
+<li><p><strong>00:03.415</strong>: <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></li>
+<li><p><strong>00:00.187</strong>: <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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.185</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.182</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
</ul>
</div>
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 c4db0eedd..8a33afc20 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:11.621</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.056</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:07.623</strong>: <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></li>
-<li><p><strong>00:03.783</strong>: <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></li>
-<li><p><strong>00:00.216</strong>: <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></li>
+<li><p><strong>00:07.209</strong>: <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></li>
+<li><p><strong>00:01.650</strong>: <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></li>
+<li><p><strong>00:00.198</strong>: <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></li>
</ul>
</div>
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 5e5058aab..6103b2262 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>00:05.647</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.530</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.047</strong>: <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></li>
-<li><p><strong>00:01.176</strong>: <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></li>
-<li><p><strong>00:00.718</strong>: <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></li>
-<li><p><strong>00:00.701</strong>: <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></li>
-<li><p><strong>00:00.309</strong>: <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></li>
-<li><p><strong>00:00.237</strong>: <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></li>
-<li><p><strong>00:00.237</strong>: <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></li>
-<li><p><strong>00:00.221</strong>: <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></li>
+<li><p><strong>00:02.048</strong>: <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></li>
+<li><p><strong>00:01.142</strong>: <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></li>
+<li><p><strong>00:00.699</strong>: <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></li>
+<li><p><strong>00:00.689</strong>: <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></li>
+<li><p><strong>00:00.293</strong>: <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></li>
+<li><p><strong>00:00.227</strong>: <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></li>
+<li><p><strong>00:00.223</strong>: <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></li>
+<li><p><strong>00:00.210</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index df5ec6b7a..d5b806ee4 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -548,8 +548,8 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [32768], []),
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpw6mx02eu/input0.cc'
-source_filename = "/tmp/tmpw6mx02eu/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp4240yq0x/input0.cc'
+source_filename = "/tmp/tmp4240yq0x/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 2b8be8b32..f7750c1a0 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ Can be the a function or the function name.</p></li>
<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">
@@ -1750,7 +1750,7 @@ the initial naive schedule (state).</p>
<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>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 1b110fe13..6f180303c 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/fcdf4636d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 284f3e1bb..63f121fcd 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/fcdf4636d/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 05cf41741..b064a396d 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/fcdf4636d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 6b56b6fc4..ea1c0e245 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/fcdf4636d/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 07f205450..bdeebc1af 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/fcdf4636d/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 72a68d4f5..8258e28cf 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/fcdf4636d/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 d8d432492..3a1c327cf 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/fcdf4636d/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 6e9e3a833..f00c30f5a 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/fcdf4636d/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/web/src/runtime.ts#L1134">runtime.ts:1134</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/fcdf4636d/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 e85b3ed34..3dd5e5326 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/fcdf4636d/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 0888f3ec3..14c554f02 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/fcdf4636d/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 81fa24686..c8f981990 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/fcdf4636d/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 a2bef202d..8351e8119 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/fcdf4636d/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 47074d70c..2a2619b66 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/fcdf4636d/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 999acc6d4..f41be4fb5 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/fcdf4636d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 dde12791c..a55210e66 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/fcdf4636d/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 82960e75a..dd9b09560 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/fcdf4636d/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 066675008..8d4ded7c5 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/fcdf4636d/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 41a4c6992..2498c4e15 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/fcdf4636d/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 aa3c16716..10352601d 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/fcdf4636d/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 e24e0e3d5..cc01ceddf 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/fcdf4636d/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 0a31107d3..9a1946e4d 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/fcdf4636d/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/web/src/runtime.ts#L1356">runtime.ts:1356</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/fcdf4636d/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 6a3178eef..f0c3b6c74 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/fcdf4636d/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 c476908bf..ba53c971a 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/fcdf4636d/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 e46cd2353..24ad056f4 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/fcdf4636d/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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/fcdf4636d/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c2744704b/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 12aabb526..73613e6ba 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 2c4a7ad71..025e43621 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:19.850</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:19.668</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:19.644</strong>: <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></li>
-<li><p><strong>00:00.207</strong>: <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></li>
+<li><p><strong>00:19.479</strong>: <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></li>
+<li><p><strong>00:00.190</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index b369815e8..aadf367e1 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -539,7 +539,7 @@ 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 21.11s!
+resnet18_v1 inference graph built in 20.83s!
</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 bc97b203d..a115ee149 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -557,7 +557,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 14.60s!
+yolov3-tiny inference graph built in 14.29s!
</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 21a5a073e..73e4f71d2 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>01:27.654</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:27.009</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:46.529</strong>: <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></li>
-<li><p><strong>00:41.125</strong>: <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></li>
+<li><p><strong>00:46.170</strong>: <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></li>
+<li><p><strong>00:40.839</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index dd61c76ab..5c22954bb 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:03.501</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.474</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.965</strong>: <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></li>
-<li><p><strong>00:00.536</strong>: <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></li>
+<li><p><strong>00:02.952</strong>: <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></li>
+<li><p><strong>00:00.521</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 9481e3758..06ccf9a07 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:00.979</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.952</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:00.495</strong>: <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></li>
-<li><p><strong>00:00.483</strong>: <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></li>
+<li><p><strong>00:00.483</strong>: <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></li>
+<li><p><strong>00:00.469</strong>: <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></li>
</ul>
</div>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 587849e46..cb2265fbc 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -544,7 +544,7 @@ operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.508 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 92.659 ms
</pre></div>
</div>
</div>
@@ -610,6 +610,7 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
+*E
</pre></div>
</div>
</div>
@@ -620,6 +621,7 @@ 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 4.190 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download 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_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index e4eaf595e..9724f3c62 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -513,7 +513,7 @@ standard deviation.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 496.7789972299988, 'median': 496.78255254999897, 'std': 0.7418708641711039}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 488.3565407600014, 'median': 488.1888957000001, 'std': 0.7026204955701438}
</pre></div>
</div>
</div>
@@ -667,129 +667,128 @@ depending on the specifics of the model and the target platform.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<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: (0/10) | 0.00 s
-[Task 1/25] Current/Best: 23.24/ 23.24 GFLOPS | Progress: (4/10) | 9.04 s
-[Task 1/25] Current/Best: 11.68/ 23.24 GFLOPS | Progress: (8/10) | 14.55 s
-[Task 1/25] Current/Best: 23.93/ 23.93 GFLOPS | Progress: (10/10) | 15.53 s Done.
+[Task 1/25] Current/Best: 13.15/ 23.43 GFLOPS | Progress: (4/10) | 4.93 s
+[Task 1/25] Current/Best: 6.43/ 23.43 GFLOPS | Progress: (8/10) | 9.01 s
+[Task 1/25] Current/Best: 14.83/ 23.43 GFLOPS | Progress: (10/10) | 10.04 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 2/25] Current/Best: 19.19/ 19.19 GFLOPS | Progress: (4/10) | 1.97 s
-[Task 2/25] Current/Best: 18.87/ 19.19 GFLOPS | Progress: (8/10) | 3.13 s
-[Task 2/25] Current/Best: 7.00/ 19.19 GFLOPS | Progress: (10/10) | 3.84 s Done.
+[Task 2/25] Current/Best: 4.19/ 15.20 GFLOPS | Progress: (4/10) | 2.07 s
+[Task 2/25] Current/Best: 21.06/ 21.06 GFLOPS | Progress: (8/10) | 3.22 s
+[Task 2/25] Current/Best: 13.14/ 21.06 GFLOPS | Progress: (10/10) | 3.84 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 3/25] Current/Best: 7.64/ 21.64 GFLOPS | Progress: (4/10) | 4.22 s
-[Task 3/25] Current/Best: 9.26/ 21.64 GFLOPS | Progress: (8/10) | 6.61 s
-[Task 3/25] Current/Best: 6.59/ 21.64 GFLOPS | Progress: (10/10) | 8.05 s Done.
+[Task 3/25] Current/Best: 8.44/ 15.69 GFLOPS | Progress: (4/10) | 3.73 s
+[Task 3/25] Current/Best: 24.09/ 24.37 GFLOPS | Progress: (8/10) | 5.44 s
+[Task 3/25] Current/Best: 19.10/ 24.37 GFLOPS | Progress: (10/10) | 6.19 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 4/25] Current/Best: 15.42/ 17.23 GFLOPS | Progress: (4/10) | 2.61 s
-[Task 4/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (8/10) | 8.40 s
-[Task 4/25] Current/Best: 16.89/ 19.95 GFLOPS | Progress: (10/10) | 9.19 s Done.
+[Task 4/25] Current/Best: 8.43/ 12.77 GFLOPS | Progress: (4/10) | 4.38 s
+[Task 4/25] Current/Best: 5.03/ 18.40 GFLOPS | Progress: (8/10) | 8.82 s
+[Task 4/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (10/10) | 10.71 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 5/25] Current/Best: 6.72/ 13.85 GFLOPS | Progress: (4/10) | 2.98 s
-[Task 5/25] Current/Best: 10.26/ 18.06 GFLOPS | Progress: (8/10) | 4.87 s
-[Task 5/25] Current/Best: 15.64/ 18.06 GFLOPS | Progress: (10/10) | 5.67 s Done.
+[Task 5/25] Current/Best: 5.80/ 16.18 GFLOPS | Progress: (4/10) | 2.98 s
+[Task 5/25] Current/Best: 17.86/ 17.86 GFLOPS | Progress: (8/10) | 5.10 s
+[Task 5/25] Current/Best: 17.48/ 17.86 GFLOPS | Progress: (10/10) | 5.82 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 6/25] Current/Best: 8.90/ 16.16 GFLOPS | Progress: (4/10) | 3.73 s
-[Task 6/25] Current/Best: 4.34/ 17.06 GFLOPS | Progress: (8/10) | 6.30 s
-[Task 6/25] Current/Best: 9.98/ 21.50 GFLOPS | Progress: (10/10) | 7.11 s Done.
+[Task 6/25] Current/Best: 15.06/ 15.49 GFLOPS | Progress: (4/10) | 3.70 s
+[Task 6/25] Current/Best: 12.00/ 15.49 GFLOPS | Progress: (8/10) | 8.02 s
+[Task 6/25] Current/Best: 5.99/ 23.22 GFLOPS | Progress: (10/10) | 9.06 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 7/25] Current/Best: 11.12/ 14.10 GFLOPS | Progress: (4/10) | 3.75 s
-[Task 7/25] Current/Best: 3.16/ 17.18 GFLOPS | Progress: (8/10) | 6.82 s
-[Task 7/25] Current/Best: 10.78/ 17.18 GFLOPS | Progress: (10/10) | 8.00 s Done.
+[Task 7/25] Current/Best: 11.04/ 18.45 GFLOPS | Progress: (4/10) | 2.82 s
+[Task 7/25] Current/Best: 15.43/ 20.90 GFLOPS | Progress: (8/10) | 4.42 s
+[Task 7/25] Current/Best: 9.26/ 20.90 GFLOPS | Progress: (10/10) | 5.56 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 8/25] Current/Best: 13.81/ 13.81 GFLOPS | Progress: (4/10) | 7.24 s
-[Task 8/25] Current/Best: 12.34/ 13.81 GFLOPS | Progress: (8/10) | 13.46 s
-[Task 8/25] Current/Best: 5.14/ 13.81 GFLOPS | Progress: (10/10) | 18.80 s Done.
+[Task 8/25] Current/Best: 10.36/ 10.36 GFLOPS | Progress: (4/10) | 4.21 s
+[Task 8/25] Current/Best: 10.10/ 15.41 GFLOPS | Progress: (8/10) | 6.89 s
+[Task 8/25] Current/Best: 18.08/ 18.08 GFLOPS | Progress: (10/10) | 7.71 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 9/25] Current/Best: 15.14/ 15.14 GFLOPS | Progress: (4/10) | 5.24 s
-[Task 9/25] Current/Best: 17.71/ 22.87 GFLOPS | Progress: (8/10) | 6.55 s
-[Task 9/25] Current/Best: 17.87/ 22.87 GFLOPS | Progress: (10/10) | 7.29 s Done.
+[Task 9/25] Current/Best: 8.52/ 16.92 GFLOPS | Progress: (4/10) | 6.65 s
+[Task 9/25] Current/Best: 7.96/ 20.75 GFLOPS | Progress: (8/10) | 11.78 s
+[Task 9/25] Current/Best: 10.00/ 20.75 GFLOPS | Progress: (10/10) | 13.15 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 10/25] Current/Best: 12.87/ 12.87 GFLOPS | Progress: (4/10) | 3.52 s
-[Task 10/25] Current/Best: 12.55/ 12.88 GFLOPS | Progress: (8/10) | 6.01 s
-[Task 10/25] Current/Best: 12.25/ 12.88 GFLOPS | Progress: (10/10) | 6.86 s Done.
+[Task 10/25] Current/Best: 13.48/ 18.47 GFLOPS | Progress: (4/10) | 2.61 s
+[Task 10/25] Current/Best: 18.03/ 18.47 GFLOPS | Progress: (8/10) | 4.53 s
+[Task 10/25] Current/Best: 22.03/ 22.03 GFLOPS | Progress: (10/10) | 5.07 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 11/25] Current/Best: 9.65/ 18.54 GFLOPS | Progress: (4/10) | 3.05 s
-[Task 11/25] Current/Best: 18.03/ 20.22 GFLOPS | Progress: (8/10) | 5.13 s
-[Task 11/25] Current/Best: 16.29/ 20.22 GFLOPS | Progress: (10/10) | 5.97 s Done.
+[Task 11/25] Current/Best: 10.72/ 21.43 GFLOPS | Progress: (4/10) | 2.93 s
+[Task 11/25] Current/Best: 19.72/ 22.95 GFLOPS | Progress: (8/10) | 4.63 s
+[Task 11/25] Current/Best: 23.01/ 23.01 GFLOPS | Progress: (10/10) | 5.89 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 12/25] Current/Best: 10.32/ 16.41 GFLOPS | Progress: (4/10) | 6.29 s
-[Task 12/25] Current/Best: 18.88/ 19.41 GFLOPS | Progress: (8/10) | 9.29 s
-[Task 12/25] Current/Best: 10.35/ 19.41 GFLOPS | Progress: (10/10) | 11.24 s Done.
+[Task 12/25] Current/Best: 15.98/ 15.98 GFLOPS | Progress: (4/10) | 2.74 s
+[Task 12/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (8/10) | 4.24 s
+[Task 12/25] Current/Best: 19.42/ 20.63 GFLOPS | Progress: (10/10) | 5.19 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 13/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (4/10) | 2.70 s
-[Task 13/25] Current/Best: 13.26/ 23.21 GFLOPS | Progress: (8/10) | 5.93 s
-[Task 13/25] Current/Best: 12.82/ 23.21 GFLOPS | Progress: (10/10) | 7.52 s Done.
+[Task 13/25] Current/Best: 12.62/ 19.09 GFLOPS | Progress: (4/10) | 4.02 s
+[Task 13/25] Current/Best: 10.27/ 19.79 GFLOPS | Progress: (8/10) | 7.36 s
+[Task 13/25] Current/Best: 10.80/ 19.79 GFLOPS | Progress: (10/10) | 8.29 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 14/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (4/10) | 6.21 s
-[Task 14/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (8/10) | 11.74 s
-[Task 14/25] Current/Best: 2.66/ 20.85 GFLOPS | Progress: (10/10) | 13.24 s Done.
+[Task 14/25] Current/Best: 14.37/ 16.20 GFLOPS | Progress: (4/10) | 4.05 s
+[Task 14/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (8/10) | 9.27 s
+[Task 14/25] Current/Best: 3.61/ 17.77 GFLOPS | Progress: (10/10) | 10.63 s Done.
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 15/25] Current/Best: 11.30/ 11.30 GFLOPS | Progress: (4/10) | 2.42 s
-[Task 15/25] Current/Best: 12.77/ 12.77 GFLOPS | Progress: (8/10) | 7.96 s
-[Task 15/25] Current/Best: 7.99/ 12.77 GFLOPS | Progress: (10/10) | 10.49 s
+[Task 15/25] Current/Best: 14.00/ 19.09 GFLOPS | Progress: (4/10) | 2.58 s
+[Task 15/25] Current/Best: 16.10/ 19.09 GFLOPS | Progress: (8/10) | 3.90 s
+[Task 15/25] Current/Best: 16.90/ 19.09 GFLOPS | Progress: (10/10) | 4.67 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 16/25] Current/Best: 6.99/ 15.69 GFLOPS | Progress: (4/10) | 2.86 s
-[Task 16/25] Current/Best: 10.33/ 20.86 GFLOPS | Progress: (8/10) | 5.12 s
-[Task 16/25] Current/Best: 6.88/ 20.86 GFLOPS | Progress: (10/10) | 5.77 s Done.
+[Task 16/25] Current/Best: 11.78/ 19.88 GFLOPS | Progress: (4/10) | 3.58 s
+[Task 16/25] Current/Best: 14.24/ 19.88 GFLOPS | Progress: (8/10) | 5.75 s
+[Task 16/25] Current/Best: 14.78/ 19.88 GFLOPS | Progress: (10/10) | 6.46 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 17/25] Current/Best: 1.56/ 14.18 GFLOPS | Progress: (4/10) | 5.00 s
-[Task 17/25] Current/Best: 3.11/ 20.91 GFLOPS | Progress: (8/10) | 7.19 s
-[Task 17/25] Current/Best: 1.56/ 20.91 GFLOPS | Progress: (10/10) | 10.69 s Done.
+[Task 17/25] Current/Best: 4.71/ 18.50 GFLOPS | Progress: (4/10) | 4.94 s
+[Task 17/25] Current/Best: 17.83/ 20.60 GFLOPS | Progress: (8/10) | 6.85 s
+[Task 17/25] Current/Best: 14.98/ 20.60 GFLOPS | Progress: (10/10) | 8.06 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 18/25] Current/Best: 10.28/ 22.20 GFLOPS | Progress: (4/10) | 3.80 s
-[Task 18/25] Current/Best: 22.07/ 22.20 GFLOPS | Progress: (8/10) | 7.60 s
-[Task 18/25] Current/Best: 19.21/ 22.20 GFLOPS | Progress: (10/10) | 8.49 s Done.
+[Task 18/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (4/10) | 2.94 s
+[Task 18/25] Current/Best: 17.51/ 19.01 GFLOPS | Progress: (8/10) | 4.84 s
+[Task 18/25] Current/Best: 10.36/ 19.27 GFLOPS | Progress: (10/10) | 5.62 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 19/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (4/10) | 4.75 s
-[Task 19/25] Current/Best: 10.33/ 20.98 GFLOPS | Progress: (8/10) | 9.95 s
-[Task 19/25] Current/Best: 20.36/ 20.98 GFLOPS | Progress: (10/10) | 11.31 s Done.
+[Task 19/25] Current/Best: 16.78/ 16.78 GFLOPS | Progress: (4/10) | 3.70 s
+[Task 19/25] Current/Best: 24.04/ 24.04 GFLOPS | Progress: (8/10) | 5.53 s
+[Task 19/25] Current/Best: 22.92/ 24.04 GFLOPS | Progress: (10/10) | 7.15 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 20/25] Current/Best: 8.43/ 18.68 GFLOPS | Progress: (4/10) | 4.18 s
-[Task 20/25] Current/Best: 8.82/ 18.68 GFLOPS | Progress: (8/10) | 11.95 s
-[Task 20/25] Current/Best: 19.00/ 19.00 GFLOPS | Progress: (10/10) | 13.09 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
- Done.
-
-[Task 21/25] Current/Best: 2.73/ 16.26 GFLOPS | Progress: (4/10) | 5.01 s
-[Task 21/25] Current/Best: 16.55/ 21.87 GFLOPS | Progress: (8/10) | 6.68 s
-[Task 21/25] Current/Best: 12.72/ 21.87 GFLOPS | Progress: (10/10) | 7.73 s
+[Task 20/25] Current/Best: 4.59/ 18.68 GFLOPS | Progress: (4/10) | 2.97 s Done.
+
+[Task 20/25] Current/Best: 8.03/ 18.68 GFLOPS | Progress: (8/10) | 4.96 s
+[Task 20/25] Current/Best: 18.54/ 18.68 GFLOPS | Progress: (10/10) | 6.19 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
+[Task 21/25] Current/Best: 8.97/ 16.75 GFLOPS | Progress: (4/10) | 2.28 s
+[Task 21/25] Current/Best: 10.16/ 22.75 GFLOPS | Progress: (8/10) | 4.63 s
+[Task 21/25] Current/Best: 5.42/ 22.75 GFLOPS | Progress: (10/10) | 5.54 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 22/25] Current/Best: 17.91/ 17.97 GFLOPS | Progress: (4/10) | 2.93 s
-[Task 22/25] Current/Best: 5.35/ 19.57 GFLOPS | Progress: (8/10) | 5.99 s
-[Task 22/25] Current/Best: 6.98/ 19.57 GFLOPS | Progress: (10/10) | 6.73 s Done.
+[Task 22/25] Current/Best: 16.27/ 16.27 GFLOPS | Progress: (4/10) | 3.24 s
+[Task 22/25] Current/Best: 9.06/ 16.27 GFLOPS | Progress: (8/10) | 4.78 s
+[Task 22/25] Current/Best: 4.90/ 16.27 GFLOPS | Progress: (10/10) | 5.70 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 23/25] Current/Best: 8.11/ 19.02 GFLOPS | Progress: (4/10) | 3.62 s
-[Task 23/25] Current/Best: 22.71/ 22.71 GFLOPS | Progress: (8/10) | 6.63 s
-[Task 23/25] Current/Best: 9.80/ 22.71 GFLOPS | Progress: (10/10) | 8.41 s Done.
+[Task 23/25] Current/Best: 9.73/ 21.94 GFLOPS | Progress: (4/10) | 3.13 s
+[Task 23/25] Current/Best: 1.55/ 21.94 GFLOPS | Progress: (8/10) | 7.46 s
+[Task 23/25] Current/Best: 14.61/ 22.86 GFLOPS | Progress: (10/10) | 8.55 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 24/25] Current/Best: 3.72/ 8.60 GFLOPS | Progress: (4/10) | 6.60 s
-[Task 24/25] Current/Best: 9.86/ 9.86 GFLOPS | Progress: (8/10) | 40.80 s
-[Task 24/25] Current/Best: 2.59/ 9.86 GFLOPS | Progress: (10/10) | 46.31 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 3.00 GFLOPS | Progress: (4/10) | 33.29 s Done.
+[Task 24/25] Current/Best: 11.11/ 11.11 GFLOPS | Progress: (4/10) | 13.03 s
+[Task 24/25] Current/Best: 9.40/ 11.11 GFLOPS | Progress: (8/10) | 20.46 s
+[Task 24/25] Current/Best: 7.73/ 11.11 GFLOPS | Progress: (10/10) | 32.12 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-[Task 25/25] Current/Best: 1.55/ 5.76 GFLOPS | Progress: (8/10) | 43.80 s
-[Task 25/25] Current/Best: 9.27/ 9.27 GFLOPS | Progress: (10/10) | 389.25 s
+[Task 25/25] Current/Best: 8.96/ 8.96 GFLOPS | Progress: (4/10) | 17.07 s
+[Task 25/25] Current/Best: 9.79/ 10.33 GFLOPS | Progress: (8/10) | 18.63 s
+[Task 25/25] Current/Best: 1.56/ 10.33 GFLOPS | Progress: (10/10) | 19.24 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -852,7 +851,7 @@ model using optimized operators to speed up our computations.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<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
+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
@@ -890,8 +889,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 458.3782529600012, 'median': 457.9627866500118, 'std': 1.3691634159363997}
-unoptimized: {'mean': 496.7789972299988, 'median': 496.78255254999897, 'std': 0.7418708641711039}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 433.50518518999934, 'median': 433.5563567999998, 'std': 0.7088809294818195}
+unoptimized: {'mean': 488.3565407600014, 'median': 488.1888957000001, 'std': 0.7026204955701438}
</pre></div>
</div>
</div>
@@ -905,7 +904,7 @@ 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> ( 13 minutes 59.777 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 43.662 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download 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 89b27f515..1a731163f 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -496,7 +496,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.269e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.248e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 2309f0a55..a0afac614 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -458,7 +458,7 @@ we can schedule the following series of operations ending with <code class="code
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xde6d130)), stage(b, placeholder(b, 0xe39b250)), 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, 0xdba3de0)), stage(b, placeholder(b, 0x5433060)), 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 [...]
</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 7b91b922b..036189bfa 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -300,20 +300,20 @@
<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>16:42.845</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>09:29.676</strong> total execution time for <strong>tutorial</strong> files:</p>
<ul class="simple">
-<li><p><strong>13:59.777</strong>: <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></li>
-<li><p><strong>00:59.798</strong>: <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></li>
-<li><p><strong>00:56.565</strong>: <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></li>
-<li><p><strong>00:26.136</strong>: <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></li>
-<li><p><strong>00:18.223</strong>: <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></li>
-<li><p><strong>00:01.213</strong>: <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></li>
-<li><p><strong>00:00.713</strong>: <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></li>
-<li><p><strong>00:00.210</strong>: <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></li>
-<li><p><strong>00:00.053</strong>: <a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></li>
-<li><p><strong>00:00.053</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
-<li><p><strong>00:00.052</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
-<li><p><strong>00:00.051</strong>: <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></li>
+<li><p><strong>06:43.662</strong>: <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></li>
+<li><p><strong>01:04.190</strong>: <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></li>
+<li><p><strong>00:57.953</strong>: <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></li>
+<li><p><strong>00:25.840</strong>: <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></li>
+<li><p><strong>00:15.753</strong>: <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></li>
+<li><p><strong>00:01.266</strong>: <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></li>
+<li><p><strong>00:00.700</strong>: <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></li>
+<li><p><strong>00:00.173</strong>: <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></li>
+<li><p><strong>00:00.037</strong>: <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></li>
+<li><p><strong>00:00.035</strong>: <a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></li>
+<li><p><strong>00:00.035</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
+<li><p><strong>00:00.032</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 680c4f30e..754b3c6d7 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -631,10 +631,10 @@ factor to be the number of threads on your CPU.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.687550000810006e-06 1.0
- naive 5.8384e-06 0.7594617269981764
-parallel 6.0158999999999994e-06 0.7825510077158689
- vector 2.45917e-05 3.1988995190156646
+ numpy 8.354089999329517e-06 1.0
+ naive 5.8574e-06 0.7011415965676816
+parallel 6.0345e-06 0.7223407936093958
+ vector 2.4573600000000005e-05 2.9415052988383215
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -952,7 +952,7 @@ matrix multiplication.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019735
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018583
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -994,7 +994,7 @@ optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.299927
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.196138
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1060,7 +1060,7 @@ schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.307180
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.298252
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1120,7 +1120,7 @@ already cache friendly from our previous optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.346809
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.333737
@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], []),
@@ -1175,7 +1175,7 @@ more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.118853
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.111516
@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], []),
@@ -1251,7 +1251,7 @@ optimized schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110135
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.107850
@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], []),
@@ -1325,7 +1325,7 @@ to `C</cite> when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110607
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110459
@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], []),
@@ -1392,7 +1392,7 @@ of thread-level parallelization.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.142828
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.143365
@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], []),
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.2999269565000007 1.0
- blocking 0.3071802152 0.09308697412072549
- vectorization 0.34680917899999997 0.10509601684269883
-loop permutation 0.1188533219 0.03601695536499369
- array packing 0.1101353187 0.03337507773711838
- block caching 0.1106073233 0.03351811260007809
- parallelization 0.1428280522 0.04328218596434862
+ none 3.1961378924000003 1.0
+ blocking 0.2982516952 0.09331627897194414
+ vectorization 0.33373664290000005 0.10441872476578133
+loop permutation 0.1115159348 0.03489083968034369
+ array packing 0.1078503934 0.03374397383055787
+ block caching 0.11045918210000001 0.03456020541624864
+ parallelization 0.14336543699999998 0.044855835957799045
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a