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 2022/07/20 12:40:11 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@7abdce26606551776e55a458622e23182e8ae9d4)
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 d1e697e08 deploying docs (apache/tvm@7abdce26606551776e55a458622e23182e8ae9d4)
d1e697e08 is described below
commit d1e697e08384aea03ec1e2e053aabd11b319c17e
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jul 20 12:40:04 2022 +0000
deploying docs (apache/tvm@7abdce26606551776e55a458622e23182e8ae9d4)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1849 ++++++++++++++++++--
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 126 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 6 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 7 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 43 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 20 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1849 ++++++++++++++++++--
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 126 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 6 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 3 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 32 +-
docs/tutorial/tensor_expr_get_started.html | 39 +-
121 files changed, 4397 insertions(+), 1154 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 9b80c5dbd..3252473c9 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.840 seconds)
+ **Total running time of the script:** ( 1 minutes 1.020 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
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 6f93188e2..7a3307b81 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip71160848-e2e7-482a-9bdf-13bf4e0ef63c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9863e8fe-a22c-4b93-a1b5-44dff10dc1d2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index 485b6e0a9..88ecca718 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 51.9MB/s]
27%|##7 | 11.3M/41.5M [00:00<00:00, 32.6MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 36.4MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 46.3MB/s]
66%|######6 | 27.4M/41.5M [00:00<00:00, 46.0MB/s]
77%|#######7 | 32.1M/41.5M [00:00<00:00, 42.0MB/s]
87%|########7 | 36.3M/41.5M [00:00<00:00, 40.5MB/s]
100%|#########9| 41.5M/41.5M [00:01<00:00, 44.3MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 42.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 57.5MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 49.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 58.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.5MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 67.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 64.2MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index d17c52c91..ae457f04f 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ 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]
8%|8 | 3.61M/44.7M [00:00<00:01, 37.6MB/s]
16%|#6 | 7.20M/44.7M [00:00<00:01, 36.8MB/s]
65%|######4 | 29.0M/44.7M [00:00<00:00, 123MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 128MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
10%|# | 4.48M/44.7M [00:00<00:00, 46.9MB/s]
21%|## | 9.29M/44.7M [00:00<00:00, 49.0MB/s]
69%|######9 | 30.8M/44.7M [00:00<00:00, 130MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 134MB/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 8fcd2668c..8b8361acd 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.194 seconds)
+ **Total running time of the script:** ( 1 minutes 6.352 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 432b2da71..f2b979fcc 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:02.865** total execution time for **how_to_compile_models** files:
+**05:03.759** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.194 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:06.352 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:02.840 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:01.020 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.669 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.458 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.643 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.142 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.124 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.349 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.069 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.923 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.339 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.927 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.943 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.795 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.438 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.410 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.373 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index dd1240763..ec79f9f15 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
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9796 15.9645 16.3803 15.7867 0.1537
+ 16.1562 16.1285 16.2919 16.0739 0.0670
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 db471bf31..02bf9e007 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
@@ -123,7 +123,7 @@ 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]
3%|2 | 5.01M/170M [00:00<00:03, 52.5MB/s]
6%|5 | 10.0M/170M [00:00<00:03, 51.1MB/s]
19%|#8 | 31.7M/170M [00:00<00:01, 130MB/s]
28%|##8 | 47.8M/170M [00:00<00:00, 145MB/s]
39%|###9 | 67.0M/170M [00:00<00:00, 166MB/s]
54%|#####3 | 91.7M/170M [00:00<00:00, 197MB/s]
69%|######8 | 117M/170M [00:00<00:00, 219MB/s]
83%|########3 | 141M/170M [00:00<00:00, 231MB/s]
97%|#########7| 165M/170M [00:00<00:00, 237MB/s]
100%|##########| 170M/170M [00:00<00:00, 193MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
11%|# | 18.1M/170M [00:00<00:00, 190MB/s]
25%|##4 | 42.0M/170M [00:00<00:00, 225MB/s]
37%|###7 | 63.5M/170M [00:00<00:00, 219MB/s]
50%|####9 | 84.4M/170M [00:00<00:00, 210MB/s]
62%|######1 | 104M/170M [00:00<00:00, 161MB/s]
74%|#######4 | 126M/170M [00:00<00:00, 179MB/s]
88%|########8 | 150M/170M [00:00<00:00, 200MB/s]
100%|##########| 170M/170M [00:00<00:00, 200MB/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').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 58.100 seconds)
+ **Total running time of the script:** ( 2 minutes 56.087 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 6bc665f3a..a262ca358 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ 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]
100%|##########| 13.6M/13.6M [00:00<00:00, 148MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 170MB/s]
@@ -412,7 +412,7 @@ 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)
- 90.3097 90.2188 95.5001 90.0878 0.5493
+ 90.4908 90.2908 102.5377 90.1410 1.2484
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.219 seconds)
+ **Total running time of the script:** ( 1 minutes 7.408 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 8a8085099..a1c0a57c9 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
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.3666 119.3138 125.7188 118.3767 0.7133
+ 119.5629 119.5468 123.8704 118.8493 0.5641
@@ -476,7 +476,7 @@ 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 57.026 seconds)
+ **Total running time of the script:** ( 1 minutes 58.215 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 f48047d50..2f5234ee5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 26.775 seconds)
+ **Total running time of the script:** ( 1 minutes 20.199 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 141a9d87c..7fadf750d 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
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6242/132723 [00:00<00:02, 62412.47KB/s]
11%|# | 14348/132723 [00:00<00:01, 73377.40KB/s]
17%|#7 | 23015/132723 [00:00<00:01, 79444.28KB/s]
24%|##3 | 31732/132723 [00:00<00:01, 82490.76KB/s]
30%|### | 40340/132723 [00:00<00:01, 83781.63KB/s]
37%|###6 | 48978/132723 [00:00<00:00, 84661.69KB/s]
43%|####3 | 57670/132723 [00:00<00:00, 85395.23KB/s]
50%|##### | 66417/132723 [00:00<00:00, 86052.97KB/s]
57%|#####6 | 75126/132723 [00:00<00:00, 86375.68KB/s]
63%|######3 | 83795/132723 [00:01<00:00, 86470.38KB/s]
70%|######9 | 92504/132723 [00:01<00:00, 86652.95KB/s]
76%|#######6 | 101176/132723 [00:01<00:00, 86670.04KB/s]
83%|########2 | 109844/132723 [00:01<00:00, 86619.66KB/s]
89%|########9 | 118506/132723 [00:01<00:00, 86488.56KB/s]
96%|#########5| 127155/132723 [00:01<00:00, 86337.09KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84646.97KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6503/132723 [00:00<00:01, 65025.88KB/s]
11%|# | 14360/132723 [00:00<00:01, 72980.97KB/s]
17%|#6 | 22132/132723 [00:00<00:01, 75143.09KB/s]
22%|##2 | 29825/132723 [00:00<00:01, 75844.02KB/s]
28%|##8 | 37648/132723 [00:00<00:01, 76697.52KB/s]
34%|###4 | 45425/132723 [00:00<00:01, 77057.65KB/s]
40%|#### | 53263/132723 [00:00<00:01, 77487.63KB/s]
46%|####6 | 61110/132723 [00:00<00:00, 77798.59KB/s]
52%|#####2 | 69041/132723 [00:00<00:00, 78269.61KB/s]
58%|#####7 | 76936/132723 [00:01<00:00, 78474.01KB/s]
64%|######3 | 84811/132723 [00:01<00:00, 78557.52KB/s]
70%|######9 | 92701/132723 [00:01<00:00, 78654.19KB/s]
76%|#######5 | 100570/132723 [00:01<00:00, 78663.87KB/s]
82%|########1 | 108437/132723 [00:01<00:00, 78598.84KB/s]
88%|########7 | 116357/132723 [00:01<00:00, 78778.65KB/s]
94%|########
#3| 124235/132723 [00:01<00:00, 78534.99KB/s]
100%|#########9| 132117/132723 [00:01<00:00, 78617.91KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77588.51KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 33.255 seconds)
+ **Total running time of the script:** ( 2 minutes 29.721 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 20031114b..6d6c55091 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
@@ -5,22 +5,22 @@
Computation times
=================
-**10:58.449** total execution time for **how_to_deploy_models** files:
+**10:43.870** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:58.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:56.087 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:33.255 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:29.721 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:57.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:58.215 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:26.775 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:20.199 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.219 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.408 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:31.806 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.276 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.261 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.957 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 98e395576..0e5459fe3 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
@@ -476,7 +476,7 @@ 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.zip694c4dbd-88a2-4811-83e0-8ae00c82bde8 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf2339388-034d-45e4-a448-b667498c18d7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -590,7 +590,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
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 1e16f713d..f19d6a503 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:40.725** total execution time for **how_to_extend_tvm** files:
+**00:39.911** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:36.740 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.232 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.187 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.954 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.976 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index f3158dd5e..4690ea87c 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6742us [6742us] (45.66%; 45.66%)
- FoldScaleAxis: 8022us [6us] (54.34%; 54.34%)
- FoldConstant: 8016us [1594us] (54.29%; 99.92%)
- InferType: 6422us [6422us] (43.49%; 80.11%)
+ InferType: 6657us [6657us] (45.52%; 45.52%)
+ FoldScaleAxis: 7967us [6us] (54.48%; 54.48%)
+ FoldConstant: 7962us [1613us] (54.44%; 99.93%)
+ InferType: 6348us [6348us] (43.41%; 79.74%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6382us [6382us] (44.63%; 44.63%)
- FoldScaleAxis: 7916us [6us] (55.37%; 55.37%)
- FoldConstant: 7911us [1623us] (55.33%; 99.93%)
- InferType: 6287us [6287us] (43.97%; 79.48%)
+ InferType: 6299us [6299us] (44.80%; 44.80%)
+ FoldScaleAxis: 7762us [6us] (55.20%; 55.20%)
+ FoldConstant: 7757us [1635us] (55.16%; 99.93%)
+ InferType: 6121us [6121us] (43.53%; 78.92%)
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 03d1b4e84..0f5bd176a 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 37.751341 ms
+ Convolution: 33.792231 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 593223c83..f51db6693 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
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.806761 ms
+ conv2d with tensor core: 13.373807 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 5bac94d82..5b4302676 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018797
- Baseline: 3.382551
+ Numpy running time: 0.018359
+ Baseline: 3.183480
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.299287
+ Opt1: 0.288408
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.339641
+ Opt2: 0.332257
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116533
+ Opt3: 0.116287
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110937
+ Opt4: 0.110389
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111563
+ Opt5: 0.111201
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.143848
+ Opt6: 0.144842
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 b25188ce0..7df9f45fd 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.514** total execution time for **how_to_optimize_operators** files:
+**00:33.712** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.138 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.310 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.333 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.377 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.025 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index a0bce9a8d..9eabe7869 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:11.384** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:04.461** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:15.205 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:21.859 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.009 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.877 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.851 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.221 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.193 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.966 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.791 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.824 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.521 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 1cec36275..9207168f7 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
@@ -241,80 +241,914 @@ cooperative fetching, unrolling and operator fusion.
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ 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" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[24] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[25] = 0f32
conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[26] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 120), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3528), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 9) + 8), 16)*9)) + floormod(threadIdx.x_2, 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 296), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
- }
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*1568)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1064), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1288), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1400), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1168)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1624), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1736), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 1848)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1848), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
}
}
}
}
for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
}
}
}
@@ -369,7 +1203,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.306 ms
+ Execution time of this operator: 0.267 ms
@@ -417,24 +1251,24 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_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=4)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_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_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
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=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
@@ -443,8 +1277,8 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_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_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
@@ -466,14 +1300,14 @@ 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=392)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=392)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ 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)
CUDA source code:
@@ -491,62 +1325,819 @@ 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__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[28];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 120) {
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 24) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 88) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 9) + 8) & 15) * 9)) + (((int)threadIdx.x) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 296) {
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
- }
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
}
}
}
for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -608,7 +2199,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 15.205 seconds)
+ **Total running time of the script:** ( 3 minutes 21.859 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 d8769c9f7..e79b378a2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.6886 9.6849 9.7070 9.6740 0.0137
+ 9.9885 9.9945 9.9959 9.9750 0.0095
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 a18f58e1b..a6895c9a6 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.7008 756.4200 757.8371 755.8453 0.8371
+ 756.4562 756.0834 757.7742 755.5110 0.9608
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.009 seconds)
+ **Total running time of the script:** ( 1 minutes 21.877 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 e76f4586e..f7a83a2fe 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
@@ -397,14 +397,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 4) {
+ let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -422,51 +422,83 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_20 + 9)
- let cse_var_16: int32 = (cse_var_20 + 8)
- let cse_var_15: int32 = (cse_var_20 + 7)
- let cse_var_14: int32 = (cse_var_20 + 6)
- let cse_var_13: int32 = (cse_var_20 + 5)
- let cse_var_12: int32 = (cse_var_20 + 4)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 2)
- let cse_var_9: int32 = (cse_var_20 + 15)
- let cse_var_8: int32 = (cse_var_20 + 14)
- let cse_var_7: int32 = (cse_var_20 + 13)
- let cse_var_6: int32 = (cse_var_20 + 12)
- let cse_var_5: int32 = (cse_var_20 + 11)
- let cse_var_4: int32 = (cse_var_20 + 10)
- let cse_var_3: int32 = (cse_var_20 + 1)
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 4) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
{
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*64) + (i.inner*16))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*64) + (i.inner*16)) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*64) + (i.inner*16)) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*64) + (i.inner*16)) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*64) + (i.inner*16)) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*64) + (i.inner*16)) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*64) + (i.inner*16)) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*64) + (i.inner*16)) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*64) + (i.inner*16)) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*64) + (i.inner*16)) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*64) + (i.inner*16)) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*64) + (i.inner*16)) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*64) + (i.inner*16)) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*64) + (i.inner*16)) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*64) + (i.inner*16)) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*64) + (i.inner*16)) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_20: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+ compute[cse_var_20] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_20]), 0f32)
+ }
}
}
}
@@ -522,7 +554,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.740 ms
+ Execution time of this operator: 2.115 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 8eac33d34..432977ccf 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:43.709** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.433** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.678 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.399 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.016 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index f4d38aa09..073eeef39 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
@@ -892,8 +892,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 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: 96.92/96.92 result: MeasureResult(costs=(0.0023885262708333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6005382537841797, timestamp=1658277851.7937653) [('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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 42.41/42.41 result: MeasureResult(costs=(0.005458684052631579,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6558880805969238, timestamp=1658314894.7212236) [('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: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1016,7 +1016,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1139,7 +1139,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1262,7 +1262,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/42.41 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
@@ -1280,7 +1280,7 @@ 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1403,7 +1403,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1526,7 +1526,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1649,7 +1649,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1772,7 +1772,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1895,7 +1895,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2018,7 +2018,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2141,7 +2141,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2264,7 +2264,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 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: 0.00/96.92 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2352,7 +2352,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fc8464d6fa2
+ 12: 0x00007fcad3cd3fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2417,7 +2417,7 @@ 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: 145.13/145.13 result: MeasureResult(costs=(0.00159518145,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4152793884277344, timestamp=1658277878.3497107) [('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: 143.61/143.61 result: MeasureResult(costs=(0.0016119724099999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4392528533935547, timestamp=1658314920.5793288) [('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
@@ -2474,7 +2474,7 @@ 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
Finish loading 20 records
- Time cost of this operator: 0.002030
+ Time cost of this operator: 0.002045
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 4821ead2d..8dee82f27 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
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.3 98.725 (1, 2, 10, 10, 3) 2 1 [309.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.026 0.966 (1, 6, 10, 10) 1 1 [3.026]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.309 (1, 1, 10, 10, 3) 1 1 [0.968]
- Total_time - 313.294 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.716 (1, 2, 10, 10, 3) 2 1 [310.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.06 0.974 (1, 6, 10, 10) 1 1 [3.06]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.311 (1, 1, 10, 10, 3) 1 1 [0.976]
+ Total_time - 314.337 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.75 96.724 (1, 6, 10, 10, 1) 2 1 [80.75]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.769 2.119 (1, 6, 10, 10) 1 1 [1.769]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.966 1.157 (1, 1, 10, 10, 3) 1 1 [0.966]
- Total_time - 83.485 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 211.0 98.575 (1, 1, 10, 10, 6) 2 1 [211.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.195 1.025 (1, 6, 10, 10) 1 1 [2.195]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.854 0.399 (1, 3, 10, 10, 1) 1 1 [0.854]
+ Total_time - 214.049 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 028c49d3e..1b3297235 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpqfeskp8y/images/random'
+ '/tmp/tmphx0n8bcl/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpqfeskp8y/images/target contains 8144 images
- /tmp/tmpqfeskp8y/images/random contains 5000 images
+ /tmp/tmphx0n8bcl/images/target contains 8144 images
+ /tmp/tmphx0n8bcl/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2217 - accuracy: 0.9247 - val_loss: 0.1436 - val_accuracy: 0.9554
+ 328/328 - 55s - loss: 0.2124 - accuracy: 0.9269 - val_loss: 0.1518 - val_accuracy: 0.9543
Epoch 2/3
- 328/328 - 52s - loss: 0.0971 - accuracy: 0.9626 - val_loss: 0.1193 - val_accuracy: 0.9607
+ 328/328 - 52s - loss: 0.0955 - accuracy: 0.9641 - val_loss: 0.1119 - val_accuracy: 0.9630
Epoch 3/3
- 328/328 - 52s - loss: 0.0672 - accuracy: 0.9757 - val_loss: 0.1559 - val_accuracy: 0.9483
+ 328/328 - 52s - loss: 0.0611 - accuracy: 0.9774 - val_loss: 0.1348 - val_accuracy: 0.9581
- <keras.callbacks.History object at 0x7f3704f74650>
+ <keras.callbacks.History object at 0x7f3484f7a9d0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 52.829 seconds)
+ **Total running time of the script:** ( 5 minutes 20.251 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index b322be5aa..c3bc60582 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
@@ -5,14 +5,14 @@
Computation times
=================
-**05:39.278** total execution time for **how_to_work_with_microtvm** files:
+**06:07.641** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:52.829 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:20.251 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.964 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.348 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.425 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 886827fb5..bd45c8d17 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:11.422** total execution time for **how_to_work_with_relay** files:
+**00:11.312** total execution time for **how_to_work_with_relay** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.918 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.830 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.498 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.476 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index c6073f63e..93878836f 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f36f93897a0>
+ <function my_cuda_math_rule at 0x7f3406b6a8c0>
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 cac905b6d..1fd2eeb26 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
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.201** total execution time for **how_to_work_with_schedules** files:
+**00:03.972** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.959 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.843 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.970 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.925 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.515 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.540 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.506 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.104 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.101 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.039 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index b71020e12..8192e985c 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1txazz30/input0.cc'\nsource_filename = \"/tmp/tmp1txazz30/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpn2rnn9c5/input0.cc'\nsource_filename = \"/tmp/tmpn2rnn9c5/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index bf06a806c..db063bbe9 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:22.155** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.927** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.148 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.921 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index f23b3cd9a..a6fceaa99 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ 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 22.71s!
+ resnet18_v1 inference graph built in 22.89s!
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 9c4e37ab5..b980ee8f7 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.13s!
+ yolov3-tiny inference graph built in 15.90s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index 15b19f83c..fd731817d 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:32.128** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.994** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.857 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.777 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.272 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.217 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 4a69c6a5f..e8c1aaa8f 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.275** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.219** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.859 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.832 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.415 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.387 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 305a23f5a..913b84881 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.752** total execution time for **topic_vta_tutorials** files:
+**00:00.712** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.383 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.352 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.329 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index c24823577..e29d68eae 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.033 ms
+ Execution time of this operator: 93.709 ms
@@ -444,6 +444,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.448 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 428c0a22b..30c02f2dc 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.60/9.60 result: MeasureResult(costs=(0.0279714158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.580247163772583, timestamp=1658276706.5162127) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.83/9.60 result: MeasureResult(costs=(0.0947328136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6668682098388672, timestamp=1658276708.7217386) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.0226696448,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.547858476638794, timestamp=1658276709.7835913) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.86/11.84 result: MeasureResult(costs=(0.144156065,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4188568592071533, timestamp=1658276712.2531645) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.66/11.84 result: MeasureResult(costs=(0.0733834168,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3123698234558105, timestamp=1658276713.6924262) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.81/11.84 result: MeasureResult(costs=(0.1482148238,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5316710472106934, timestamp=1658276716.2684035) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.84 result: MeasureResult(costs=(0.3093142214,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.068036317825317, timestamp=1658276721.9126203) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.67/11.84 result: MeasureResult(costs=(0.0251498804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5481252670288086, timestamp=1658276722.4770162) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.92/11.84 result: MeasureResult(costs=(0.1401543738,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.341982841491699, timestamp=1658276724.939115) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.77/11.84 result: MeasureResult(costs=(0.09675427839999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.650031328201294, timestamp=1658276726.6481774) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.61/10.61 result: MeasureResult(costs=(0.025309163000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5352621078491211, timestamp=1658313760.5466416) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.95/10.61 result: MeasureResult(costs=(0.0908508776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5931732654571533, timestamp=1658313762.1632085) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.89/11.89 result: MeasureResult(costs=(0.02257131,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5658528804779053, timestamp=1658313763.1961055) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.86/11.89 result: MeasureResult(costs=(0.1442857984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.451098918914795, timestamp=1658313766.198497) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.71/11.89 result: MeasureResult(costs=(0.07243789279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2908518314361572, timestamp=1658313767.6192424) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.83/11.89 result: MeasureResult(costs=(0.14637800299999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5062406063079834, timestamp=1658313770.1671727) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.89 result: MeasureResult(costs=(0.30789154939999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0476601123809814, timestamp=1658313775.7699413) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.84/11.89 result: MeasureResult(costs=(0.0247564598,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.538102388381958, timestamp=1658313776.3280804) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.92/11.89 result: MeasureResult(costs=(0.1401542054,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.340850591659546, timestamp=1658313778.7886598) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.80/11.89 result: MeasureResult(costs=(0.095994948,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6429662704467773, timestamp=1658313780.4889681) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index ab3b56e21..c45d3544e 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 493.59745205998934, 'median': 493.46763434998593, 'std': 0.9481906503805504}
+ {'mean': 493.53625042998374, 'median': 493.4867044999919, 'std': 0.6957633864636172}
@@ -563,31 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.38/ 17.38 GFLOPS | Progress: (4/20) | 6.26 s
[Task 1/25] Current/Best: 6.14/ 17.38 GFLOPS | Progress: (8/20) | 9.27 s
[Task 1/25] Current/Best: 11.56/ 22.78 GFLOPS | Progress: (12/20) | 11.74 s
[Task 1/25] Current/Best: 16.78/ 22.78 GFLOPS | Progress: (16/20) | 13.42 s
[Task 1/25] Current/Best: 11.59/ 23.84 GFLOPS | Progress: (20/20) | 15.15 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.30/ 13.02 GFLOPS | Progress: (4/20) | 3.77 s
[Task 2/25] Current/Best: 14.06/ 17.66 GFLOPS | Progress: (8/20) | 5.06 s
[Task 2/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (12/20) | 6.41 s
[Task 2/25] Current/Best: 11.92/ 20.50 GFLOPS | Progress: (16/20) | 7.68 s
[Task 2/25] Current/Best: 18.46/ 20.50 GFLOPS | Progress: (20/20) | 9.30 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.55 GFLOPS | Progress: (4/20) | 5.87 s
[Task 3/25] Current/Best: 15.58/ 16.82 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 14.90/ 16.82 GFLOPS | Progress: (12/20) | 9.49 s
[Task 3/25] Current/Best: 7.21/ 23.79 GFLOPS | Progress: (16/20) | 11.41 s
[Task 3/25] Current/Best: 12.66/ 23.79 GFLOPS | Progress: (20/20) | 16.00 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.52 GFLOPS | Progress: (4/20) | 2.38 s
[Task 4/25] Current/Best: 6.57/ 20.52 GFLOPS | Progress: (8/20) | 7.18 s
[Task 4/25] Current/Best: 21.60/ 21.60 GFLOPS | Progress: (12/20) | 12.22 s
[Task 4/25] Current/Best: 16.89/ 21.60 GFLOPS | Progress: (16/20) | 14.62 s
[Task 4/25] Current/Best: 13.37/ 21.60 GFLOPS | Progress: (20/20) | 16.69 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.70/ 10.30 GFLOPS | Progress: (4/20) | 2.61 s
[Task 5/25] Current/Best: 11.82/ 12.86 GFLOPS | Progress: (8/20) | 4.67 s
[Task 5/25] Current/Best: 11.41/ 18.10 GFLOPS | Progress: (12/20) | 7.89 s
[Task 5/25] Current/Best: 11.65/ 22.62 GFLOPS | Progress: (16/20) | 9.31 s
[Task 5/25] Current/Best: 12.07/ 22.62 GFLOPS | Progress: (20/20) | 11.23 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.33/ 20.66 GFLOPS | Progress: (4/20) | 4.13 s
[Task 6/25] Current/Best: 19.05/ 20.66 GFLOPS | Progress: (8/20) | 5.89 s
[Task 6/25] Current/Best: 13.34/ 20.66 GFLOPS | Progress: (12/20) | 7.84 s
[Task 6/25] Current/Best: 19.92/ 20.66 GFLOPS | Progress: (16/20) | 10.10 s
[Task 6/25] Current/Best: 3.73/ 20.66 GFLOPS | Progress: (20/20) | 12.60 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.10/ 12.59 GFLOPS | Progress: (4/20) | 3.65 s
[Task 7/25] Current/Best: 20.14/ 21.02 GFLOPS | Progress: (8/20) | 5.17 s
[Task 7/25] Current/Best: 16.13/ 21.02 GFLOPS | Progress: (12/20) | 7.09 s
[Task 7/25] Current/Best: 12.26/ 21.02 GFLOPS | Progress: (16/20) | 9.14 s
[Task 7/25] Current/Best: 6.33/ 21.70 GFLOPS | Progress: (20/20) | 11.61 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.40/ 14.04 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.79/ 14.04 GFLOPS | Progress: (8/20) | 8.14 s
[Task 8/25] Current/Best: 13.16/ 14.04 GFLOPS | Progress: (12/20) | 14.72 s
[Task 8/25] Current/Best: 18.54/ 18.54 GFLOPS | Progress: (16/20) | 16.80 s
[Task 8/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (20/20) | 23.99 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.22/ 15.80 GFLOPS | Progress: (4/20) | 11.94 s
[Task 9/25] Current/Best: 23.38/ 23.38 GFLOPS | Progress: (8/20) | 13.75 s
[Task 9/25] Current/Best: 6.95/ 23.38 GFLOPS | Progress: (12/20) | 16.34 s
[Task 9/25] Current/Best: 17.73/ 23.38 GFLOPS | Progress: (16/20) | 19.12 s
[Task 9/25] Current/Best: 9.09/ 23.38 GFLOPS | Progress: (20/20) | 27.77 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.36/ 18.36 GFLOPS | Progress: (4/20) | 2.57 s
[Task 10/25] Current/Best: 15.30/ 18.36 GFLOPS | Progress: (8/20) | 4.21 s
[Task 10/25] Current/Best: 12.34/ 19.22 GFLOPS | Progress: (12/20) | 5.75 s
[Task 10/25] Current/Best: 18.99/ 20.43 GFLOPS | Progress: (16/20) | 6.87 s
[Task 10/25] Current/Best: 8.84/ 20.43 GFLOPS | Progress: (20/20
) | 8.42 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.12/ 18.01 GFLOPS | Progress: (4/20) | 3.36 s
[Task 11/25] Current/Best: 15.16/ 18.01 GFLOPS | Progress: (8/20) | 6.19 s
[Task 11/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 8.27 s
[Task 11/25] Current/Best: 12.83/ 21.21 GFLOPS | Progress: (16/20) | 11.25 s
[Task 11/25] Current/Best: 19.46/ 21.46 GFLOPS | Progress: (20/20) | 13.37 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.77/ 18.06 GFLOPS | Progress: (4/20) | 5.81 s
[Task 12/25] Current/Best: 5.30/ 18.06 GFLOPS | Progress: (8/20) | 9.75 s
[Task 12/25] Current/Best: 18.81/ 19.02 GFLOPS | Progress: (12/20) | 11.73 s
[Task 12/25] Current/Best: 15.42/ 19.02 GFLOPS | Progress: (16/20) | 14.69 s
[Task 12/25] Current/Best: 15.14/ 19.02 GFLOPS | Progress: (20/20) | 16.63 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.80/ 17.32 GFLOPS | Progress: (4/20) | 3.77 s
[Task 13/25] Current/Best: 15.72/ 20.84 GFLOPS | Progress: (8/20) | 6.38 s
[Task 13/25] Current/Best: 19.65/ 21.78 GFLOPS | Progress: (12/20) | 9.41 s
[Task 13/25] Current/Best: 12.23/ 21.78 GFLOPS | Progress: (16/20) | 12.88 s
[Task 13/25] Current/Best: 18.74/ 21.78 GFLOPS | Progress: (20/20) | 15.25 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.56/ 13.56 GFLOPS | Progress: (4/20) | 3.45 s
[Task 14/25] Current/Best: 6.08/ 13.56 GFLOPS | Progress: (8/20) | 5.68 s
[Task 14/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (12/20) | 8.35 s
[Task 14/25] Current/Best: 16.63/ 20.48 GFLOPS | Progress: (16/20) | 10.04 s Done.
-
[Task 14/25] Current/Best: 17.33/ 20.48 GFLOPS | Progress: (20/20) | 11.78 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.16/ 17.66 GFLOPS | Progress: (4/20) | 2.74 s
[Task 15/25] Current/Best: 14.31/ 18.09 GFLOPS | Progress: (8/20) | 4.08 s
[Task 15/25] Current/Best: 10.39/ 22.25 GFLOPS | Progress: (12/20) | 6.36 s
[Task 15/25] Current/Best: 20.37/ 22.25 GFLOPS | Progress: (16/20) | 9.53 s
[Task 15/25] Current/Best: 9.69/ 22.25 GFLOPS | Progress: (20/20) | 10.55 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.31/ 20.31 GFLOPS | Progress: (4/20) | 2.96 s
[Task 16/25] Current/Best: 3.04/ 20.31 GFLOPS | Progress: (8/20) | 4.60 s
[Task 16/25] Current/Best: 19.71/ 20.31 GFLOPS | Progress: (12/20) | 5.83 s
[Task 16/25] Current/Best: 17.23/ 20.31 GFLOPS | Progress: (16/20) |
7.20 s
[Task 16/25] Current/Best: 10.01/ 21.77 GFLOPS | Progress: (20/20) | 9.38 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.89/ 18.88 GFLOPS | Progress: (4/20) | 4.83 s
[Task 17/25] Current/Best: 14.23/ 23.21 GFLOPS | Progress: (8/20) | 7.63 s
[Task 17/25] Current/Best: 16.88/ 23.21 GFLOPS | Progress: (12/20) | 9.70 s
[Task 17/25] Current/Best: 16.46/ 23.21 GFLOPS | Progress: (16/20) | 11.93 s
[Task 17/25] Current/Best: 10.03/ 23.21 GFLOPS | Progress: (20/20) | 14.12 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.12/ 18.19 GFLOPS | Progress: (4/20) | 3.86 s
[Task 18/25] Current/Best: 10.55/ 18.60 GFLOPS | Progress: (8/20) | 7.56 s
[Task 18/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (12/20) | 9.48 s
[Task 18/25] Current/Best: 10.02/ 19.13 GFLOPS | Progress: (16/20) | 13.40 s
[Task 18/25] Current/Best: 20.80/ 20.80 GFLOPS | Progress: (20/20) | 14.91 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.04/ 20.36 GFLOPS | Progress: (4/20) | 6.18 s
[Task 19/25] Current/Best: 2.61/ 20.36 GFLOPS | Progress: (8/20) | 9.52 s
[Task 19/25] Current/Best: 20.22/ 20.36 GFLOPS | Progress: (12/20) | 12.47 s
[Task 19/25] Current/Best: 14.58/ 21.85 GFLOPS | Progress: (16/20) | 15.50 s
[Task 19/25] Current/Best: 2.70/ 23.66 GFLOPS | Progress: (20/20) | 18.28 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.03/ 15.53 GFLOPS | Progress: (4/20) | 3.31 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (4/20) | 6.30 s
[Task 1/25] Current/Best: 6.16/ 17.47 GFLOPS | Progress: (8/20) | 9.21 s
[Task 1/25] Current/Best: 11.50/ 22.78 GFLOPS | Progress: (12/20) | 11.69 s
[Task 1/25] Current/Best: 16.77/ 22.78 GFLOPS | Progress: (16/20) | 13.39 s
[Task 1/25] Current/Best: 11.61/ 23.93 GFLOPS | Progress: (20/20) | 15.12 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.20/ 13.30 GFLOPS | Progress: (4/20) | 3.92 s
[Task 2/25] Current/Best: 14.13/ 18.42 GFLOPS | Progress: (8/20) | 5.24 s
[Task 2/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (12/20) | 6.56 s
[Task 2/25] Current/Best: 12.43/ 20.73 GFLOPS | Progress: (16/20) | 7.83 s
[Task 2/25] Current/Best: 19.33/ 20.73 GFLOPS | Progress: (20/20) | 9.44 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.54 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.55/ 16.81 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 14.91/ 16.81 GFLOPS | Progress: (12/20) | 9.49 s
[Task 3/25] Current/Best: 7.13/ 23.70 GFLOPS | Progress: (16/20) | 11.40 s
[Task 3/25] Current/Best: 12.63/ 23.70 GFLOPS | Progress: (20/20) | 15.95 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.50/ 20.36 GFLOPS | Progress: (4/20) | 2.38 s
[Task 4/25] Current/Best: 6.85/ 20.36 GFLOPS | Progress: (8/20) | 7.14 s
[Task 4/25] Current/Best: 22.32/ 22.32 GFLOPS | Progress: (12/20) | 12.15 s
[Task 4/25] Current/Best: 16.51/ 22.32 GFLOPS | Progress: (16/20) | 14.58 s
[Task 4/25] Current/Best: 13.39/ 22.32 GFLOPS | Progress: (20/20) | 16.63 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.92/ 10.57 GFLOPS | Progress: (4/20) | 2.55 s
[Task 5/25] Current/Best: 11.87/ 13.13 GFLOPS | Progress: (8/20) | 4.60 s
[Task 5/25] Current/Best: 11.56/ 18.05 GFLOPS | Progress: (12/20) | 7.82 s
[Task 5/25] Current/Best: 11.85/ 22.73 GFLOPS | Progress: (16/20) | 9.26 s
[Task 5/25] Current/Best: 12.05/ 22.73 GFLOPS | Progress: (20/20) | 11.14 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.17/ 20.64 GFLOPS | Progress: (4/20) | 4.09 s
[Task 6/25] Current/Best: 18.92/ 20.64 GFLOPS | Progress: (8/20) | 5.86 s
[Task 6/25] Current/Best: 13.28/ 20.64 GFLOPS | Progress: (12/20) | 7.80 s
[Task 6/25] Current/Best: 20.03/ 20.64 GFLOPS | Progress: (16/20) | 10.05 s
[Task 6/25] Current/Best: 3.76/ 20.64 GFLOPS | Progress: (20/20) | 12.55 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.14/ 12.86 GFLOPS | Progress: (4/20) | 3.65 s
[Task 7/25] Current/Best: 20.31/ 21.20 GFLOPS | Progress: (8/20) | 5.17 s
[Task 7/25] Current/Best: 16.18/ 21.20 GFLOPS | Progress: (12/20) | 7.07 s
[Task 7/25] Current/Best: 12.20/ 21.20 GFLOPS | Progress: (16/20) | 9.09 s
[Task 7/25] Current/Best: 6.48/ 21.81 GFLOPS | Progress: (20/20) | 11.53 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.98/ 14.03 GFLOPS | Progress: (4/20) | 2.88 s
[Task 8/25] Current/Best: 9.60/ 14.03 GFLOPS | Progress: (8/20) | 8.05 s
[Task 8/25] Current/Best: 12.68/ 14.03 GFLOPS | Progress: (12/20) | 14.51 s
[Task 8/25] Current/Best: 18.76/ 18.76 GFLOPS | Progress: (16/20) | 16.59 s
[Task 8/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (20/20) | 23.68 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.28/ 15.68 GFLOPS | Progress: (4/20) | 11.93 s
[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.71 s
[Task 9/25] Current/Best: 8.24/ 23.47 GFLOPS | Progress: (12/20) | 16.24 s
[Task 9/25] Current/Best: 17.76/ 23.47 GFLOPS | Progress: (16/20) | 19.04 s
[Task 9/25] Current/Best: 9.25/ 23.47 GFLOPS | Progress: (20/20) | 27.83 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (4/20) | 2.56 s
[Task 10/25] Current/Best: 15.51/ 18.07 GFLOPS | Progress: (8/20) | 4.21 s
[Task 10/25] Current/Best: 12.77/ 18.80 GFLOPS | Progress: (12/20) | 5.75 s
[Task 10/25] Current/Best: 19.10/ 20.29 GFLOPS | Progress: (16/20) | 6.87 s
[Task 10/25] Current/Best: 8.79/ 20.29 GFLOPS | Progress: (20/20
) | 8.38 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.32/ 18.06 GFLOPS | Progress: (4/20) | 3.35 s
[Task 11/25] Current/Best: 16.92/ 18.06 GFLOPS | Progress: (8/20) | 6.16 s
[Task 11/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (12/20) | 8.20 s
[Task 11/25] Current/Best: 13.10/ 21.09 GFLOPS | Progress: (16/20) | 11.19 s
[Task 11/25] Current/Best: 19.43/ 21.56 GFLOPS | Progress: (20/20) | 13.30 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.14 GFLOPS | Progress: (4/20) | 5.69 s
[Task 12/25] Current/Best: 5.34/ 18.14 GFLOPS | Progress: (8/20) | 9.65 s
[Task 12/25] Current/Best: 18.72/ 18.92 GFLOPS | Progress: (12/20) | 11.62 s
[Task 12/25] Current/Best: 15.34/ 18.92 GFLOPS | Progress: (16/20) | 14.57 s
[Task 12/25] Current/Best: 15.19/ 19.04 GFLOPS | Progress: (20/20) | 16.48 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.75/ 17.32 GFLOPS | Progress: (4/20) | 3.74 s
[Task 13/25] Current/Best: 15.69/ 21.16 GFLOPS | Progress: (8/20) | 6.35 s
[Task 13/25] Current/Best: 19.60/ 21.85 GFLOPS | Progress: (12/20) | 9.33 s
[Task 13/25] Current/Best: 12.27/ 21.85 GFLOPS | Progress: (16/20) | 12.77 s
[Task 13/25] Current/Best: 18.30/ 21.85 GFLOPS | Progress: (20/20) | 15.07 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.54/ 13.24 GFLOPS | Progress: (4/20) | 3.41 s
[Task 14/25] Current/Best: 6.12/ 13.36 GFLOPS | Progress: (8/20) | 5.55 s
[Task 14/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (12/20) | 8.23 s
[Task 14/25] Current/Best: 17.06/ 20.65 GFLOPS | Progress: (16/20) | 9.91 s Done.
+
[Task 14/25] Current/Best: 17.20/ 20.65 GFLOPS | Progress: (20/20) | 11.65 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.02/ 17.60 GFLOPS | Progress: (4/20) | 2.71 s
[Task 15/25] Current/Best: 14.45/ 18.01 GFLOPS | Progress: (8/20) | 4.05 s
[Task 15/25] Current/Best: 10.39/ 22.20 GFLOPS | Progress: (12/20) | 6.30 s
[Task 15/25] Current/Best: 20.42/ 22.20 GFLOPS | Progress: (16/20) | 9.36 s
[Task 15/25] Current/Best: 9.69/ 22.20 GFLOPS | Progress: (20/20) | 10.37 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.52/ 20.52 GFLOPS | Progress: (4/20) | 3.02 s
[Task 16/25] Current/Best: 2.97/ 20.52 GFLOPS | Progress: (8/20) | 4.63 s
[Task 16/25] Current/Best: 19.75/ 20.52 GFLOPS | Progress: (12/20) | 5.84 s
[Task 16/25] Current/Best: 17.90/ 20.52 GFLOPS | Progress: (16/20) |
7.21 s
[Task 16/25] Current/Best: 10.04/ 22.15 GFLOPS | Progress: (20/20) | 9.37 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.79/ 18.65 GFLOPS | Progress: (4/20) | 4.81 s
[Task 17/25] Current/Best: 14.42/ 23.44 GFLOPS | Progress: (8/20) | 7.58 s
[Task 17/25] Current/Best: 16.94/ 23.44 GFLOPS | Progress: (12/20) | 9.66 s
[Task 17/25] Current/Best: 16.50/ 23.44 GFLOPS | Progress: (16/20) | 11.93 s
[Task 17/25] Current/Best: 10.00/ 23.44 GFLOPS | Progress: (20/20) | 14.09 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.19/ 18.13 GFLOPS | Progress: (4/20) | 3.82 s
[Task 18/25] Current/Best: 10.58/ 20.13 GFLOPS | Progress: (8/20) | 7.51 s
[Task 18/25] Current/Best: 19.36/ 20.13 GFLOPS | Progress: (12/20) | 9.43 s
[Task 18/25] Current/Best: 10.01/ 20.13 GFLOPS | Progress: (16/20) | 13.30 s
[Task 18/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (20/20) | 14.81 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.16/ 20.17 GFLOPS | Progress: (4/20) | 6.09 s
[Task 19/25] Current/Best: 2.61/ 20.17 GFLOPS | Progress: (8/20) | 9.40 s
[Task 19/25] Current/Best: 19.34/ 20.86 GFLOPS | Progress: (12/20) | 12.38 s
[Task 19/25] Current/Best: 14.12/ 21.41 GFLOPS | Progress: (16/20) | 15.39 s
[Task 19/25] Current/Best: 2.70/ 23.51 GFLOPS | Progress: (20/20) | 18.19 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.96/ 15.22 GFLOPS | Progress: (4/20) | 3.35 s Done.
Done.
-
[Task 20/25] Current/Best: 9.77/ 15.53 GFLOPS | Progress: (8/20) | 6.82 s
[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.74 s
[Task 20/25] Current/Best: 12.26/ 16.60 GFLOPS | Progress: (16/20) | 14.50 s
[Task 20/25] Current/Best: 10.87/ 22.04 GFLOPS | Progress: (20/20) | 16.61 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.75 GFLOPS | Progress: (4/20) | 3.28 s
[Task 21/25] Current/Best: 14.66/ 17.75 GFLOPS | Progress: (8/20) | 4.89 s
[Task 21/25] Current/Best: 1.61/ 17.75 GFLOPS | Progress: (12/20) | 7.01 s
[Task 21/25] Current/Best: 17.69/ 17.75 GFLOPS | Progress: (16/20) | 10.53 s
[Task 21/25] Current/Best: 4.47/ 17.75 GFLOPS | Progress: (20/20) | 17.88 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.96 GFLOPS | Progress: (4/20
) | 2.68 s
[Task 22/25] Current/Best: 8.76/ 21.57 GFLOPS | Progress: (8/20) | 4.73 s
[Task 22/25] Current/Best: 19.89/ 21.57 GFLOPS | Progress: (12/20) | 7.09 s
[Task 22/25] Current/Best: 15.48/ 21.57 GFLOPS | Progress: (16/20) | 9.24 s
[Task 22/25] Current/Best: 14.56/ 21.57 GFLOPS | Progress: (20/20) | 10.91 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 16.15/ 20.35 GFLOPS | Progress: (4/20) | 3.27 s
[Task 23/25] Current/Best: 15.27/ 20.35 GFLOPS | Progress: (8/20) | 6.62 s
[Task 23/25] Current/Best: 20.92/ 21.74 GFLOPS | Progress: (12/20) | 8.46 s
[Task 23/25] Current/Best: 6.36/ 21.74 GFLOPS | Progress: (16/20) | 15.60 s
[Task 23/25] Current/Best: 7.75/ 21.74 GFLOPS | Progress: (20/20) | 19.81 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.82 s
[Task 24/25] Current/Best: 2.14/ 8.58 GFLOPS | Progress: (8/20) | 22.82 s
[Task 24/25] Current/Best: 4.54/ 8.58 GFLOPS | Progress: (12/20) | 34.35 s Done.
- Done.
-
[Task 24/25] Current/Best: 6.32/ 8.94 GFLOPS | Progress: (16/20) | 40.09 s
[Task 24/25] Current/Best: 3.30/ 9.16 GFLOPS | Progress: (20/20) | 46.08 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.77 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 5.93/ 8.10 GFLOPS | Progress: (8/20) | 22.89 s
[Task 25/25] Current/Best: 6.01/ 8.10 GFLOPS | Progress: (12/20) | 34.34 s
[Task 25/25] Current/Best: 5.89/ 8.86 GFLOPS | Progress: (16/20) | 36.24 s
[Task 25/25] Current/Best: 2.85/ 8.86 GFLOPS | Progress: (20/20) | 46.93 s
+
[Task 20/25] Current/Best: 9.82/ 15.22 GFLOPS | Progress: (8/20) | 6.89 s
[Task 20/25] Current/Best: 2.32/ 16.47 GFLOPS | Progress: (12/20) | 10.86 s
[Task 20/25] Current/Best: 12.59/ 16.47 GFLOPS | Progress: (16/20) | 14.64 s
[Task 20/25] Current/Best: 12.49/ 22.01 GFLOPS | Progress: (20/20) | 16.79 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.70 GFLOPS | Progress: (4/20) | 3.29 s
[Task 21/25] Current/Best: 14.66/ 17.70 GFLOPS | Progress: (8/20) | 4.88 s
[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 7.02 s
[Task 21/25] Current/Best: 18.03/ 18.03 GFLOPS | Progress: (16/20) | 10.55 s
[Task 21/25] Current/Best: 4.47/ 18.03 GFLOPS | Progress: (20/20) | 17.95 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.98 GFLOPS | Progress: (4/20
) | 2.69 s
[Task 22/25] Current/Best: 9.07/ 21.93 GFLOPS | Progress: (8/20) | 4.72 s
[Task 22/25] Current/Best: 19.93/ 21.93 GFLOPS | Progress: (12/20) | 7.11 s
[Task 22/25] Current/Best: 15.28/ 21.93 GFLOPS | Progress: (16/20) | 9.23 s
[Task 22/25] Current/Best: 14.29/ 21.93 GFLOPS | Progress: (20/20) | 10.98 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.55/ 20.67 GFLOPS | Progress: (4/20) | 3.24 s
[Task 23/25] Current/Best: 14.86/ 20.67 GFLOPS | Progress: (8/20) | 6.61 s
[Task 23/25] Current/Best: 20.94/ 21.85 GFLOPS | Progress: (12/20) | 8.46 s
[Task 23/25] Current/Best: 6.47/ 21.85 GFLOPS | Progress: (16/20) | 15.55 s
[Task 23/25] Current/Best: 7.88/ 21.85 GFLOPS | Progress: (20/20) | 19.76 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.63/ 8.63 GFLOPS | Progress: (4/20) | 11.78 s
[Task 24/25] Current/Best: 3.49/ 8.63 GFLOPS | Progress: (8/20) | 23.01 s
[Task 24/25] Current/Best: 4.57/ 8.63 GFLOPS | Progress: (12/20) | 33.74 s Done.
+
[Task 24/25] Current/Best: 7.06/ 8.86 GFLOPS | Progress: (16/20) | 39.45 s
[Task 24/25] Current/Best: 3.39/ 8.87 GFLOPS | Progress: (20/20) | 45.44 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.80 GFLOPS | Progress: (4/20) | 11.59 s
[Task 25/25] Current/Best: 5.66/ 7.91 GFLOPS | Progress: (8/20) | 22.86 s
[Task 25/25] Current/Best: 5.87/ 7.91 GFLOPS | Progress: (12/20) | 34.26 s
[Task 25/25] Current/Best: 5.77/ 9.73 GFLOPS | Progress: (16/20) | 36.15 s
[Task 25/25] Current/Best: 2.86/ 9.73 GFLOPS | Progress: (20/20) | 46.82 s
@@ -655,6 +654,7 @@ model using optimized operators to speed up our computations.
.. code-block:: none
+ Done.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 406.3042897299965, 'median': 406.1970731999736, 'std': 0.8946138427652085}
- unoptimized: {'mean': 493.59745205998934, 'median': 493.46763434998593, 'std': 0.9481906503805504}
+ optimized: {'mean': 411.43764090000786, 'median': 410.83044350000364, 'std': 1.5720975136900446}
+ unoptimized: {'mean': 493.53625042998374, 'median': 493.4867044999919, 'std': 0.6957633864636172}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 24.011 seconds)
+ **Total running time of the script:** ( 10 minutes 25.530 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 8f771082b..8755c93bb 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.26e-07 secs/op
+ 1.274e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 525012764..d35b4360b 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x230601c0)), stage(b, placeholder(b, 0x2189e0d0)), 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(mi [...]
+ [stage(a, placeholder(a, 0x21009a60)), stage(b, placeholder(b, 0x23ea9590)), 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(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 8ec88fac0..da04114aa 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:18.018** total execution time for **tutorial** files:
+**13:20.482** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:24.011 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:25.530 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.927 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:02.448 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:57.373 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.187 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.376 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:29.645 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.665 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.335 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.785 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.690 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.706 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.501 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.140 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 4f89ec2e7..e77f080f9 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.334119997925882e-06 1.0
- naive 5.876399999999999e-06 0.7051014385996917
- parallel 6.1097e-06 0.7330947960337174
- vector 2.47353e-05 2.96795582570876
+ numpy 7.78187999912916e-06 1.0
+ naive 5.897e-06 0.7577860363639519
+ parallel 6.1382e-06 0.7887811172476191
+ vector 2.4624099999999997e-05 3.164286779384363
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019171
+ Numpy running time: 0.018387
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.389451
+ none: 3.216035
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.315025
+ blocking: 0.304432
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.346574
+ vectorization: 0.330172
@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], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.116758
+ loop permutation: 0.117172
@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], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.108431
+ array packing: 0.110589
@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], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.110439
+ block caching: 0.110728
@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], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.143562
+ parallelization: 0.144745
@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], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3894509828000006 1.0
- blocking 0.31502492179999997 0.09294275780904204
- vectorization 0.3465738924 0.10225074625911772
- loop permutation 0.1167580677 0.03444748671466168
- array packing 0.10843139289999999 0.0319908426026051
- block caching 0.11043853320000001 0.0325830152908031
- parallelization 0.1435622937 0.04235561877971289
+ none 3.2160349806999995 1.0
+ blocking 0.3044323477 0.09466077002487626
+ vectorization 0.3301723251 0.10266440728456722
+ loop permutation 0.1171718934 0.03643365016337492
+ array packing 0.1105888571 0.034386708404499165
+ block caching 0.1107275236 0.03442982562829561
+ parallelization 0.14474488 0.04500724677083424
@@ -1686,11 +1686,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.927 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 5db55c92d..80b4c97f8 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-eb7cf7051dd239ef86db13875687ef6d5ebb9418
+7abdce26606551776e55a458622e23182e8ae9d4
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index e7cd034b7..5c3ae5204 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -569,7 +569,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.840 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.020 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 9bdc9e547..9e9623ade 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip71160848-e2e7-482a-9bdf-13bf4e0ef63c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9863e8fe-a22c-4b93-a1b5-44dff10dc1d2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index bf634715f..0bcbe5344 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,15 +427,12 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 51.9MB/s]
- 27%|##7 | 11.3M/41.5M [00:00<00:00, 32.6MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 36.4MB/s]
- 54%|#####4 | 22.5M/41.5M [00:00<00:00, 46.3MB/s]
- 66%|######6 | 27.4M/41.5M [00:00<00:00, 46.0MB/s]
- 77%|#######7 | 32.1M/41.5M [00:00<00:00, 42.0MB/s]
- 87%|########7 | 36.3M/41.5M [00:00<00:00, 40.5MB/s]
-100%|#########9| 41.5M/41.5M [00:01<00:00, 44.3MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 42.5MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 57.5MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 49.0MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 58.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.5MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00<00:00, 67.9MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 64.2MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 527b6a847..f4d5d75dc 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,10 +409,10 @@ 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]
- 8%|8 | 3.61M/44.7M [00:00<00:01, 37.6MB/s]
- 16%|#6 | 7.20M/44.7M [00:00<00:01, 36.8MB/s]
- 65%|######4 | 29.0M/44.7M [00:00<00:00, 123MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 128MB/s]
+ 10%|# | 4.48M/44.7M [00:00<00:00, 46.9MB/s]
+ 21%|## | 9.29M/44.7M [00:00<00:00, 49.0MB/s]
+ 69%|######9 | 30.8M/44.7M [00:00<00:00, 130MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 134MB/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 f44b5e176..3b134d346 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ 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 3.194 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.352 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 2e296922f..1d0d0daa5 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:02.865</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:03.759</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,43 +331,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:03.194</p></td>
+<td><p>01:06.352</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:02.840</p></td>
+<td><p>01:01.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:39.669</p></td>
+<td><p>00:39.458</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:27.615</p></td>
+<td><p>00:27.643</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:26.142</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:25.124</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.349</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:25.069</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.923</p></td>
+<td><p>00:23.339</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.927</p></td>
+<td><p>00:19.943</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:13.795</p></td>
+<td><p>00:13.438</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.410</p></td>
+<td><p>00:02.373</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index cbf322894..daf0005a6 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9796 15.9645 16.3803 15.7867 0.1537
+ 16.1562 16.1285 16.2919 16.0739 0.0670
</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 567807c4c..93839257a 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,16 +431,14 @@ 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]
- 3%|2 | 5.01M/170M [00:00<00:03, 52.5MB/s]
- 6%|5 | 10.0M/170M [00:00<00:03, 51.1MB/s]
- 19%|#8 | 31.7M/170M [00:00<00:01, 130MB/s]
- 28%|##8 | 47.8M/170M [00:00<00:00, 145MB/s]
- 39%|###9 | 67.0M/170M [00:00<00:00, 166MB/s]
- 54%|#####3 | 91.7M/170M [00:00<00:00, 197MB/s]
- 69%|######8 | 117M/170M [00:00<00:00, 219MB/s]
- 83%|########3 | 141M/170M [00:00<00:00, 231MB/s]
- 97%|#########7| 165M/170M [00:00<00:00, 237MB/s]
-100%|##########| 170M/170M [00:00<00:00, 193MB/s]
+ 11%|# | 18.1M/170M [00:00<00:00, 190MB/s]
+ 25%|##4 | 42.0M/170M [00:00<00:00, 225MB/s]
+ 37%|###7 | 63.5M/170M [00:00<00:00, 219MB/s]
+ 50%|####9 | 84.4M/170M [00:00<00:00, 210MB/s]
+ 62%|######1 | 104M/170M [00:00<00:00, 161MB/s]
+ 74%|#######4 | 126M/170M [00:00<00:00, 179MB/s]
+ 88%|########8 | 150M/170M [00:00<00:00, 200MB/s]
+100%|##########| 170M/170M [00:00<00:00, 200MB/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').
@@ -535,7 +533,7 @@ 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> ( 2 minutes 58.100 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 56.087 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 482f7dee6..0c9d2dfdc 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -475,7 +475,7 @@ 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]
-100%|##########| 13.6M/13.6M [00:00<00:00, 148MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 170MB/s]
</pre></div>
</div>
</div>
@@ -564,7 +564,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3097 90.2188 95.5001 90.0878 0.5493
+ 90.4908 90.2908 102.5377 90.1410 1.2484
</pre></div>
</div>
<div class="admonition note">
@@ -603,7 +603,7 @@ 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 8.219 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.408 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index a389afdf4..de6772c16 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -568,7 +568,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.3666 119.3138 125.7188 118.3767 0.7133
+ 119.5629 119.5468 123.8704 118.8493 0.5641
</pre></div>
</div>
<div class="admonition note">
@@ -596,7 +596,7 @@ 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 57.026 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.215 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 675f07355..e01393122 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ 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 26.775 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.199 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 72e6c925c..92e909bb3 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,22 +436,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6242/132723 [00:00<00:02, 62412.47KB/s]
- 11%|# | 14348/132723 [00:00<00:01, 73377.40KB/s]
- 17%|#7 | 23015/132723 [00:00<00:01, 79444.28KB/s]
- 24%|##3 | 31732/132723 [00:00<00:01, 82490.76KB/s]
- 30%|### | 40340/132723 [00:00<00:01, 83781.63KB/s]
- 37%|###6 | 48978/132723 [00:00<00:00, 84661.69KB/s]
- 43%|####3 | 57670/132723 [00:00<00:00, 85395.23KB/s]
- 50%|##### | 66417/132723 [00:00<00:00, 86052.97KB/s]
- 57%|#####6 | 75126/132723 [00:00<00:00, 86375.68KB/s]
- 63%|######3 | 83795/132723 [00:01<00:00, 86470.38KB/s]
- 70%|######9 | 92504/132723 [00:01<00:00, 86652.95KB/s]
- 76%|#######6 | 101176/132723 [00:01<00:00, 86670.04KB/s]
- 83%|########2 | 109844/132723 [00:01<00:00, 86619.66KB/s]
- 89%|########9 | 118506/132723 [00:01<00:00, 86488.56KB/s]
- 96%|#########5| 127155/132723 [00:01<00:00, 86337.09KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 84646.97KB/s]
+ 5%|4 | 6503/132723 [00:00<00:01, 65025.88KB/s]
+ 11%|# | 14360/132723 [00:00<00:01, 72980.97KB/s]
+ 17%|#6 | 22132/132723 [00:00<00:01, 75143.09KB/s]
+ 22%|##2 | 29825/132723 [00:00<00:01, 75844.02KB/s]
+ 28%|##8 | 37648/132723 [00:00<00:01, 76697.52KB/s]
+ 34%|###4 | 45425/132723 [00:00<00:01, 77057.65KB/s]
+ 40%|#### | 53263/132723 [00:00<00:01, 77487.63KB/s]
+ 46%|####6 | 61110/132723 [00:00<00:00, 77798.59KB/s]
+ 52%|#####2 | 69041/132723 [00:00<00:00, 78269.61KB/s]
+ 58%|#####7 | 76936/132723 [00:01<00:00, 78474.01KB/s]
+ 64%|######3 | 84811/132723 [00:01<00:00, 78557.52KB/s]
+ 70%|######9 | 92701/132723 [00:01<00:00, 78654.19KB/s]
+ 76%|#######5 | 100570/132723 [00:01<00:00, 78663.87KB/s]
+ 82%|########1 | 108437/132723 [00:01<00:00, 78598.84KB/s]
+ 88%|########7 | 116357/132723 [00:01<00:00, 78778.65KB/s]
+ 94%|#########3| 124235/132723 [00:01<00:00, 78534.99KB/s]
+100%|#########9| 132117/132723 [00:01<00:00, 78617.91KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 77588.51KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -494,7 +496,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 33.255 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 29.721 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 1a1f573a5..acdc7d9ef 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:58.449</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:43.870</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:58.100</p></td>
+<td><p>02:56.087</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:33.255</p></td>
+<td><p>02:29.721</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:57.026</p></td>
+<td><p>01:58.215</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:26.775</p></td>
+<td><p>01:20.199</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:08.219</p></td>
+<td><p>01:07.408</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:31.806</p></td>
+<td><p>00:29.276</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:23.261</p></td>
+<td><p>00:22.957</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 3df7ed032..d549988c0 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -607,7 +607,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip694c4dbd-88a2-4811-83e0-8ae00c82bde8 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.zipf2339388-034d-45e4-a448-b667498c18d7 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>
@@ -671,7 +671,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index b646e7dc7..f8a3b0514 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.725</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:39.911</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.531</p></td>
+<td><p>00:36.740</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.232</p></td>
+<td><p>00:02.187</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.954</p></td>
+<td><p>00:00.976</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 3ca67dd38..5bce4e9f5 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6742us [6742us] (45.66%; 45.66%)
-FoldScaleAxis: 8022us [6us] (54.34%; 54.34%)
- FoldConstant: 8016us [1594us] (54.29%; 99.92%)
- InferType: 6422us [6422us] (43.49%; 80.11%)
+InferType: 6657us [6657us] (45.52%; 45.52%)
+FoldScaleAxis: 7967us [6us] (54.48%; 54.48%)
+ FoldConstant: 7962us [1613us] (54.44%; 99.93%)
+ InferType: 6348us [6348us] (43.41%; 79.74%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6382us [6382us] (44.63%; 44.63%)
-FoldScaleAxis: 7916us [6us] (55.37%; 55.37%)
- FoldConstant: 7911us [1623us] (55.33%; 99.93%)
- InferType: 6287us [6287us] (43.97%; 79.48%)
+InferType: 6299us [6299us] (44.80%; 44.80%)
+FoldScaleAxis: 7762us [6us] (55.20%; 55.20%)
+ FoldConstant: 7757us [1635us] (55.16%; 99.93%)
+ InferType: 6121us [6121us] (43.53%; 78.92%)
</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 a3914204b..ff14858ec 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -559,7 +559,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 37.751341 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 33.792231 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 1fb222dd8..fe2798a54 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -901,7 +901,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.806761 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.373807 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 4a7a45e8c..7670dfbb7 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -456,8 +456,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018797
-Baseline: 3.382551
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018359
+Baseline: 3.183480
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -517,7 +517,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.299287
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.288408
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -584,7 +584,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.339641
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332257
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -645,7 +645,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116533
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116287
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -728,7 +728,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110937
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110389
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -814,7 +814,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111563
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111201
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -904,7 +904,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.143848
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144842
</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 ae97707a5..590ac4f80 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.514</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:33.712</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.138</p></td>
+<td><p>00:31.310</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.333</p></td>
+<td><p>00:01.377</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.043</p></td>
+<td><p>00:01.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index aeec8f463..e01b6633c 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:11.384</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:04.461</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:15.205</p></td>
+<td><p>03:21.859</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:23.009</p></td>
+<td><p>01:21.877</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:45.851</p></td>
+<td><p>00:45.221</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:29.529</p></td>
+<td><p>00:18.193</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.966</p></td>
+<td><p>00:08.791</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.824</p></td>
+<td><p>00:08.521</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 55b6119f5..558ba8a41 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
@@ -487,80 +487,914 @@ cooperative fetching, unrolling and operator fusion.</p>
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ 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" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[24] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[25] = 0f32
conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[26] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 120), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3528), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 9) + 8), 16)*9)) + floormod(threadIdx.x_2, 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 296), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*36)) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
- }
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*1568)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1064), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1288), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1400), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1168)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1624), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1736), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 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 + 1848)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1848), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*504) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
}
}
}
}
for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
}
}
}
@@ -597,7 +1431,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.306 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.267 ms
</pre></div>
</div>
</div>
@@ -626,24 +1460,24 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_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=4)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_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_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
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=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
@@ -652,8 +1486,8 @@ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_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_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
@@ -675,14 +1509,14 @@ 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=392)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=392)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+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)
CUDA source code:
@@ -700,62 +1534,819 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[28];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 120) {
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 24) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 88) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 9) + 8) & 15) * 9)) + (((int)threadIdx.x) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 296) {
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 36)) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
- }
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ 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) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
}
}
}
for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -792,7 +2383,7 @@ 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> ( 3 minutes 15.205 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 21.859 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 18e2fc5d2..f3f944073 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ 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)
- 9.6886 9.6849 9.7070 9.6740 0.0137
+ 9.9885 9.9945 9.9959 9.9750 0.0095
</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 6825e630f..501c5a44c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.7008 756.4200 757.8371 755.8453 0.8371
+ 756.4562 756.0834 757.7742 755.5110 0.9608
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ 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 23.009 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.877 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 2a221ddf8..c4fddc1d1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,14 +620,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 4) {
+ let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -645,51 +645,83 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_20 + 9)
- let cse_var_16: int32 = (cse_var_20 + 8)
- let cse_var_15: int32 = (cse_var_20 + 7)
- let cse_var_14: int32 = (cse_var_20 + 6)
- let cse_var_13: int32 = (cse_var_20 + 5)
- let cse_var_12: int32 = (cse_var_20 + 4)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 2)
- let cse_var_9: int32 = (cse_var_20 + 15)
- let cse_var_8: int32 = (cse_var_20 + 14)
- let cse_var_7: int32 = (cse_var_20 + 13)
- let cse_var_6: int32 = (cse_var_20 + 12)
- let cse_var_5: int32 = (cse_var_20 + 11)
- let cse_var_4: int32 = (cse_var_20 + 10)
- let cse_var_3: int32 = (cse_var_20 + 1)
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 4) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
{
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*64) + (i.inner*16))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*64) + (i.inner*16)) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*64) + (i.inner*16)) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*64) + (i.inner*16)) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*64) + (i.inner*16)) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*64) + (i.inner*16)) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*64) + (i.inner*16)) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*64) + (i.inner*16)) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*64) + (i.inner*16)) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*64) + (i.inner*16)) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*64) + (i.inner*16)) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*64) + (i.inner*16)) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*64) + (i.inner*16)) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*64) + (i.inner*16)) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*64) + (i.inner*16)) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*64) + (i.inner*16)) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_20: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+ compute[cse_var_20] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_20]), 0f32)
+ }
}
}
}
@@ -727,7 +759,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.740 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.115 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 93fdfd374..2a103b5f0 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.709</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.433</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:43.678</p></td>
+<td><p>00:43.399</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.016</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index e68f35faa..30f63a2f1 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1167,8 +1167,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 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: 96.92/96.92 result: MeasureResult(costs=(0.0023885262708333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6005382537841797, timestamp=1658277851.7937653) [('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: 0.00/96.92 result: Traceback (most recent call last):
+No: 6 GFLOPS: 42.41/42.41 result: MeasureResult(costs=(0.005458684052631579,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6558880805969238, timestamp=1658314894.7212236) [('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: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1291,7 +1291,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1414,7 +1414,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1537,7 +1537,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/42.41 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
@@ -1555,7 +1555,7 @@ No: 10 GFLOPS: 0.00/96.92 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1678,7 +1678,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1801,7 +1801,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1924,7 +1924,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2047,7 +2047,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2170,7 +2170,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2293,7 +2293,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2416,7 +2416,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2539,7 +2539,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 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: 0.00/96.92 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2627,7 +2627,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fc8464d6fa2
+ 12: 0x00007fcad3cd3fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2692,7 +2692,7 @@ 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: 145.13/145.13 result: MeasureResult(costs=(0.00159518145,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4152793884277344, timestamp=1658277878.3497107) [('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: 143.61/143.61 result: MeasureResult(costs=(0.0016119724099999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4392528533935547, timestamp=1658314920.5793288) [('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,
@@ -2733,7 +2733,7 @@ and measure running time.</p>
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
Finish loading 20 records
-Time cost of this operator: 0.002030
+Time cost of this operator: 0.002045
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index cd278feb5..51ea7c21e 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.3 98.725 (1, 2, 10, 10, 3) 2 1 [309.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.026 0.966 (1, 6, 10, 10) 1 1 [3.026]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.309 (1, 1, 10, 10, 3) 1 1 [0.968]
-Total_time - 313.294 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.716 (1, 2, 10, 10, 3) 2 1 [310.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.06 0.974 (1, 6, 10, 10) 1 1 [3.06]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.311 (1, 1, 10, 10, 3) 1 1 [0.976]
+Total_time - 314.337 - - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.75 96.724 (1, 6, 10, 10, 1) 2 1 [80.75]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.769 2.119 (1, 6, 10, 10) 1 1 [1.769]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.966 1.157 (1, 1, 10, 10, 3) 1 1 [0.966]
-Total_time - 83.485 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 211.0 98.575 (1, 1, 10, 10, 6) 2 1 [211.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.195 1.025 (1, 6, 10, 10) 1 1 [2.195]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.854 0.399 (1, 3, 10, 10, 1) 1 1 [0.854]
+Total_time - 214.049 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index d9e6167f5..b72f0c311 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpqfeskp8y/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmphx0n8bcl/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpqfeskp8y/images/target contains 8144 images
-/tmp/tmpqfeskp8y/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmphx0n8bcl/images/target contains 8144 images
+/tmp/tmphx0n8bcl/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2217 - accuracy: 0.9247 - val_loss: 0.1436 - val_accuracy: 0.9554
+328/328 - 55s - loss: 0.2124 - accuracy: 0.9269 - val_loss: 0.1518 - val_accuracy: 0.9543
Epoch 2/3
-328/328 - 52s - loss: 0.0971 - accuracy: 0.9626 - val_loss: 0.1193 - val_accuracy: 0.9607
+328/328 - 52s - loss: 0.0955 - accuracy: 0.9641 - val_loss: 0.1119 - val_accuracy: 0.9630
Epoch 3/3
-328/328 - 52s - loss: 0.0672 - accuracy: 0.9757 - val_loss: 0.1559 - val_accuracy: 0.9483
+328/328 - 52s - loss: 0.0611 - accuracy: 0.9774 - val_loss: 0.1348 - val_accuracy: 0.9581
-<keras.callbacks.History object at 0x7f3704f74650>
+<keras.callbacks.History object at 0x7f3484f7a9d0>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 52.829 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 20.251 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 6fd68f213..ced06d460 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:39.278</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:07.641</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:52.829</p></td>
+<td><p>05:20.251</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:43.098</p></td>
+<td><p>00:43.964</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.348</p></td>
+<td><p>00:03.425</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index a642a8daa..d72c0c009 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:11.422</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.312</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.918</p></td>
+<td><p>00:09.830</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.498</p></td>
+<td><p>00:01.476</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index cf49c31ba..147bbc45d 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -517,7 +517,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f36f93897a0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f3406b6a8c0>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index ad458d8ef..26b3d0611 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.201</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:03.972</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.959</p></td>
+<td><p>00:01.843</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.970</p></td>
+<td><p>00:00.925</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.546</p></td>
+<td><p>00:00.515</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.540</p></td>
+<td><p>00:00.506</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.104</p></td>
+<td><p>00:00.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.040</p></td>
+<td><p>00:00.039</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index a1cfed9d5..e1f942c35 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -572,7 +572,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1txazz30/input0.cc'\nsource_filename = \"/tmp/tmp1txazz30/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpn2rnn9c5/input0.cc'\nsource_filename = \"/tmp/tmpn2rnn9c5/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index d2f11fef7..8f0ca6d0b 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1597,7 +1597,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1881,7 +1881,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index db6507990..f482a65b4 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/eb7cf7051/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 d0f274978..20546df06 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/eb7cf7051/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 4c45d532c..9c8fa0423 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/eb7cf7051/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 89763eacc..b59af5662 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/eb7cf7051/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 424aedda6..ebe4b2344 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/eb7cf7051/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 5ffb9b64b..6455af952 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/eb7cf7051/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 215a207f4..41d1efb21 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/eb7cf7051/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 cec76950e..ef42d0800 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/eb7cf7051/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/web/src/runtime.ts#L1140">runtime.ts:1140</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/eb7cf7051/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 9e56a7357..e89b92527 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/eb7cf7051/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 eba13df03..3ebdd77d4 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/eb7cf7051/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 354ea568b..e4b2111d2 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/eb7cf7051/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 5bfdf6d04..f287a477f 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/eb7cf7051/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 e0492f745..52078ead8 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/eb7cf7051/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 a75b46b8e..170bcfa22 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/eb7cf7051/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 dd6f03c0d..dfe5553e0 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/eb7cf7051/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 e320fdf6d..345694941 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/eb7cf7051/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 1eee9e797..3bb2c0717 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/eb7cf7051/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 59f1a761e..6a315b0d3 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/eb7cf7051/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 e0cacfb88..e77851e9f 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/eb7cf7051/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 7e3c6212c..034dbac01 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/eb7cf7051/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 2749c6612..937e6de79 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/eb7cf7051/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/web/src/runtime.ts#L1362">runtime.ts:1362</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/eb7cf7051/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 eddc16539..3680e6269 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/eb7cf7051/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 51edcc02c..6e237ee7b 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/eb7cf7051/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 72581bab9..40b4be6fd 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/eb7cf7051/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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/eb7cf7051/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7abdce266/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 e9ce0a02c..95953348f 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 d4a0332ac..6bf9ac604 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:22.155</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.927</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -331,7 +331,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:22.148</p></td>
+<td><p>00:20.921</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 086f4048b..385c7a012 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ 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 22.71s!
+resnet18_v1 inference graph built in 22.89s!
</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 2c7a277d2..70101c87f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.13s!
+yolov3-tiny inference graph built in 15.90s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index e114673bb..3470cbddf 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:32.128</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.994</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.857</p></td>
+<td><p>00:48.777</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:43.272</p></td>
+<td><p>00:43.217</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index f25649525..22ccab325 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.275</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.219</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.859</p></td>
+<td><p>00:02.832</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.415</p></td>
+<td><p>00:00.387</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index ba3767ad2..d58a93978 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.752</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.712</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.400</p></td>
+<td><p>00:00.383</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.352</p></td>
+<td><p>00:00.329</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index b2071d7a7..464ae4a30 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -561,7 +561,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.033 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.709 ms
</pre></div>
</div>
</div>
@@ -635,6 +635,7 @@ 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 2.448 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 6be44797f..20210f0ea 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -663,16 +663,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 9.60/9.60 result: MeasureResult(costs=(0.0279714158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.580247163772583, timestamp=1658276706.5162127) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.83/9.60 result: MeasureResult(costs=(0.0947328136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6668682098388672, timestamp=1658276708.7217386) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.0226696448,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.547858476638794, timestamp=1658276709.7835913) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.86/11.84 result: MeasureResult(costs=(0.144156065,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4188568592071533, timestamp=1658276712.2531645) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.66/11.84 result: MeasureResult(costs=(0.0733834168,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3123698234558105, timestamp=1658276713.6924262) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.81/11.84 result: MeasureResult(costs=(0.1482148238,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5316710472106934, timestamp=1658276716.2684035) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.84 result: MeasureResult(costs=(0.3093142214,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.068036317825317, timestamp=1658276721.9126203) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.67/11.84 result: MeasureResult(costs=(0.0251498804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5481252670288086, timestamp=1658276722.4770162) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.92/11.84 result: MeasureResult(costs=(0.1401543738,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.341982841491699, timestamp=1658276724.939115) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.77/11.84 result: MeasureResult(costs=(0.09675427839999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.650031328201294, timestamp=1658276726.6481774) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.61/10.61 result: MeasureResult(costs=(0.025309163000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5352621078491211, timestamp=1658313760.5466416) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.95/10.61 result: MeasureResult(costs=(0.0908508776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5931732654571533, timestamp=1658313762.1632085) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.89/11.89 result: MeasureResult(costs=(0.02257131,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5658528804779053, timestamp=1658313763.1961055) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.86/11.89 result: MeasureResult(costs=(0.1442857984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.451098918914795, timestamp=1658313766.198497) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.71/11.89 result: MeasureResult(costs=(0.07243789279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2908518314361572, timestamp=1658313767.6192424) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.83/11.89 result: MeasureResult(costs=(0.14637800299999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5062406063079834, timestamp=1658313770.1671727) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.89 result: MeasureResult(costs=(0.30789154939999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0476601123809814, timestamp=1658313775.7699413) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.84/11.89 result: MeasureResult(costs=(0.0247564598,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.538102388381958, timestamp=1658313776.3280804) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.92/11.89 result: MeasureResult(costs=(0.1401542054,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.340850591659546, timestamp=1658313778.7886598) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.80/11.89 result: MeasureResult(costs=(0.095994948,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6429662704467773, timestamp=1658313780.4889681) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 8354e6086..acf8a67ae 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -545,7 +545,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.59745205998934, 'median': 493.46763434998593, 'std': 0.9481906503805504}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.53625042998374, 'median': 493.4867044999919, 'std': 0.6957633864636172}
</pre></div>
</div>
</div>
@@ -700,179 +700,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.38/ 17.38 GFLOPS | Progress: (4/20) | 6.26 s
-[Task 1/25] Current/Best: 6.14/ 17.38 GFLOPS | Progress: (8/20) | 9.27 s
-[Task 1/25] Current/Best: 11.56/ 22.78 GFLOPS | Progress: (12/20) | 11.74 s
-[Task 1/25] Current/Best: 16.78/ 22.78 GFLOPS | Progress: (16/20) | 13.42 s
-[Task 1/25] Current/Best: 11.59/ 23.84 GFLOPS | Progress: (20/20) | 15.15 s Done.
+[Task 1/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (4/20) | 6.30 s
+[Task 1/25] Current/Best: 6.16/ 17.47 GFLOPS | Progress: (8/20) | 9.21 s
+[Task 1/25] Current/Best: 11.50/ 22.78 GFLOPS | Progress: (12/20) | 11.69 s
+[Task 1/25] Current/Best: 16.77/ 22.78 GFLOPS | Progress: (16/20) | 13.39 s
+[Task 1/25] Current/Best: 11.61/ 23.93 GFLOPS | Progress: (20/20) | 15.12 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.30/ 13.02 GFLOPS | Progress: (4/20) | 3.77 s
-[Task 2/25] Current/Best: 14.06/ 17.66 GFLOPS | Progress: (8/20) | 5.06 s
-[Task 2/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (12/20) | 6.41 s
-[Task 2/25] Current/Best: 11.92/ 20.50 GFLOPS | Progress: (16/20) | 7.68 s
-[Task 2/25] Current/Best: 18.46/ 20.50 GFLOPS | Progress: (20/20) | 9.30 s Done.
+[Task 2/25] Current/Best: 12.20/ 13.30 GFLOPS | Progress: (4/20) | 3.92 s
+[Task 2/25] Current/Best: 14.13/ 18.42 GFLOPS | Progress: (8/20) | 5.24 s
+[Task 2/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (12/20) | 6.56 s
+[Task 2/25] Current/Best: 12.43/ 20.73 GFLOPS | Progress: (16/20) | 7.83 s
+[Task 2/25] Current/Best: 19.33/ 20.73 GFLOPS | Progress: (20/20) | 9.44 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 10.55 GFLOPS | Progress: (4/20) | 5.87 s
-[Task 3/25] Current/Best: 15.58/ 16.82 GFLOPS | Progress: (8/20) | 7.78 s
-[Task 3/25] Current/Best: 14.90/ 16.82 GFLOPS | Progress: (12/20) | 9.49 s
-[Task 3/25] Current/Best: 7.21/ 23.79 GFLOPS | Progress: (16/20) | 11.41 s
-[Task 3/25] Current/Best: 12.66/ 23.79 GFLOPS | Progress: (20/20) | 16.00 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.54 GFLOPS | Progress: (4/20) | 5.85 s
+[Task 3/25] Current/Best: 15.55/ 16.81 GFLOPS | Progress: (8/20) | 7.78 s
+[Task 3/25] Current/Best: 14.91/ 16.81 GFLOPS | Progress: (12/20) | 9.49 s
+[Task 3/25] Current/Best: 7.13/ 23.70 GFLOPS | Progress: (16/20) | 11.40 s
+[Task 3/25] Current/Best: 12.63/ 23.70 GFLOPS | Progress: (20/20) | 15.95 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.56/ 20.52 GFLOPS | Progress: (4/20) | 2.38 s
-[Task 4/25] Current/Best: 6.57/ 20.52 GFLOPS | Progress: (8/20) | 7.18 s
-[Task 4/25] Current/Best: 21.60/ 21.60 GFLOPS | Progress: (12/20) | 12.22 s
-[Task 4/25] Current/Best: 16.89/ 21.60 GFLOPS | Progress: (16/20) | 14.62 s
-[Task 4/25] Current/Best: 13.37/ 21.60 GFLOPS | Progress: (20/20) | 16.69 s Done.
+[Task 4/25] Current/Best: 9.50/ 20.36 GFLOPS | Progress: (4/20) | 2.38 s
+[Task 4/25] Current/Best: 6.85/ 20.36 GFLOPS | Progress: (8/20) | 7.14 s
+[Task 4/25] Current/Best: 22.32/ 22.32 GFLOPS | Progress: (12/20) | 12.15 s
+[Task 4/25] Current/Best: 16.51/ 22.32 GFLOPS | Progress: (16/20) | 14.58 s
+[Task 4/25] Current/Best: 13.39/ 22.32 GFLOPS | Progress: (20/20) | 16.63 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.70/ 10.30 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 5/25] Current/Best: 11.82/ 12.86 GFLOPS | Progress: (8/20) | 4.67 s
-[Task 5/25] Current/Best: 11.41/ 18.10 GFLOPS | Progress: (12/20) | 7.89 s
-[Task 5/25] Current/Best: 11.65/ 22.62 GFLOPS | Progress: (16/20) | 9.31 s
-[Task 5/25] Current/Best: 12.07/ 22.62 GFLOPS | Progress: (20/20) | 11.23 s Done.
+[Task 5/25] Current/Best: 9.92/ 10.57 GFLOPS | Progress: (4/20) | 2.55 s
+[Task 5/25] Current/Best: 11.87/ 13.13 GFLOPS | Progress: (8/20) | 4.60 s
+[Task 5/25] Current/Best: 11.56/ 18.05 GFLOPS | Progress: (12/20) | 7.82 s
+[Task 5/25] Current/Best: 11.85/ 22.73 GFLOPS | Progress: (16/20) | 9.26 s
+[Task 5/25] Current/Best: 12.05/ 22.73 GFLOPS | Progress: (20/20) | 11.14 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.33/ 20.66 GFLOPS | Progress: (4/20) | 4.13 s
-[Task 6/25] Current/Best: 19.05/ 20.66 GFLOPS | Progress: (8/20) | 5.89 s
-[Task 6/25] Current/Best: 13.34/ 20.66 GFLOPS | Progress: (12/20) | 7.84 s
-[Task 6/25] Current/Best: 19.92/ 20.66 GFLOPS | Progress: (16/20) | 10.10 s
-[Task 6/25] Current/Best: 3.73/ 20.66 GFLOPS | Progress: (20/20) | 12.60 s Done.
+[Task 6/25] Current/Best: 12.17/ 20.64 GFLOPS | Progress: (4/20) | 4.09 s
+[Task 6/25] Current/Best: 18.92/ 20.64 GFLOPS | Progress: (8/20) | 5.86 s
+[Task 6/25] Current/Best: 13.28/ 20.64 GFLOPS | Progress: (12/20) | 7.80 s
+[Task 6/25] Current/Best: 20.03/ 20.64 GFLOPS | Progress: (16/20) | 10.05 s
+[Task 6/25] Current/Best: 3.76/ 20.64 GFLOPS | Progress: (20/20) | 12.55 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 10.10/ 12.59 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 7/25] Current/Best: 20.14/ 21.02 GFLOPS | Progress: (8/20) | 5.17 s
-[Task 7/25] Current/Best: 16.13/ 21.02 GFLOPS | Progress: (12/20) | 7.09 s
-[Task 7/25] Current/Best: 12.26/ 21.02 GFLOPS | Progress: (16/20) | 9.14 s
-[Task 7/25] Current/Best: 6.33/ 21.70 GFLOPS | Progress: (20/20) | 11.61 s Done.
+[Task 7/25] Current/Best: 11.14/ 12.86 GFLOPS | Progress: (4/20) | 3.65 s
+[Task 7/25] Current/Best: 20.31/ 21.20 GFLOPS | Progress: (8/20) | 5.17 s
+[Task 7/25] Current/Best: 16.18/ 21.20 GFLOPS | Progress: (12/20) | 7.07 s
+[Task 7/25] Current/Best: 12.20/ 21.20 GFLOPS | Progress: (16/20) | 9.09 s
+[Task 7/25] Current/Best: 6.48/ 21.81 GFLOPS | Progress: (20/20) | 11.53 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.40/ 14.04 GFLOPS | Progress: (4/20) | 2.91 s
-[Task 8/25] Current/Best: 9.79/ 14.04 GFLOPS | Progress: (8/20) | 8.14 s
-[Task 8/25] Current/Best: 13.16/ 14.04 GFLOPS | Progress: (12/20) | 14.72 s
-[Task 8/25] Current/Best: 18.54/ 18.54 GFLOPS | Progress: (16/20) | 16.80 s
-[Task 8/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (20/20) | 23.99 s Done.
+[Task 8/25] Current/Best: 9.98/ 14.03 GFLOPS | Progress: (4/20) | 2.88 s
+[Task 8/25] Current/Best: 9.60/ 14.03 GFLOPS | Progress: (8/20) | 8.05 s
+[Task 8/25] Current/Best: 12.68/ 14.03 GFLOPS | Progress: (12/20) | 14.51 s
+[Task 8/25] Current/Best: 18.76/ 18.76 GFLOPS | Progress: (16/20) | 16.59 s
+[Task 8/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (20/20) | 23.68 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.22/ 15.80 GFLOPS | Progress: (4/20) | 11.94 s
-[Task 9/25] Current/Best: 23.38/ 23.38 GFLOPS | Progress: (8/20) | 13.75 s
-[Task 9/25] Current/Best: 6.95/ 23.38 GFLOPS | Progress: (12/20) | 16.34 s
-[Task 9/25] Current/Best: 17.73/ 23.38 GFLOPS | Progress: (16/20) | 19.12 s
-[Task 9/25] Current/Best: 9.09/ 23.38 GFLOPS | Progress: (20/20) | 27.77 s
+[Task 9/25] Current/Best: 14.28/ 15.68 GFLOPS | Progress: (4/20) | 11.93 s
+[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.71 s
+[Task 9/25] Current/Best: 8.24/ 23.47 GFLOPS | Progress: (12/20) | 16.24 s
+[Task 9/25] Current/Best: 17.76/ 23.47 GFLOPS | Progress: (16/20) | 19.04 s
+[Task 9/25] Current/Best: 9.25/ 23.47 GFLOPS | Progress: (20/20) | 27.83 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.36/ 18.36 GFLOPS | Progress: (4/20) | 2.57 s
-[Task 10/25] Current/Best: 15.30/ 18.36 GFLOPS | Progress: (8/20) | 4.21 s
-[Task 10/25] Current/Best: 12.34/ 19.22 GFLOPS | Progress: (12/20) | 5.75 s
-[Task 10/25] Current/Best: 18.99/ 20.43 GFLOPS | Progress: (16/20) | 6.87 s
-[Task 10/25] Current/Best: 8.84/ 20.43 GFLOPS | Progress: (20/20) | 8.42 s Done.
+[Task 10/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (4/20) | 2.56 s
+[Task 10/25] Current/Best: 15.51/ 18.07 GFLOPS | Progress: (8/20) | 4.21 s
+[Task 10/25] Current/Best: 12.77/ 18.80 GFLOPS | Progress: (12/20) | 5.75 s
+[Task 10/25] Current/Best: 19.10/ 20.29 GFLOPS | Progress: (16/20) | 6.87 s
+[Task 10/25] Current/Best: 8.79/ 20.29 GFLOPS | Progress: (20/20) | 8.38 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.12/ 18.01 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 11/25] Current/Best: 15.16/ 18.01 GFLOPS | Progress: (8/20) | 6.19 s
-[Task 11/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 8.27 s
-[Task 11/25] Current/Best: 12.83/ 21.21 GFLOPS | Progress: (16/20) | 11.25 s
-[Task 11/25] Current/Best: 19.46/ 21.46 GFLOPS | Progress: (20/20) | 13.37 s Done.
+[Task 11/25] Current/Best: 12.32/ 18.06 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 11/25] Current/Best: 16.92/ 18.06 GFLOPS | Progress: (8/20) | 6.16 s
+[Task 11/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (12/20) | 8.20 s
+[Task 11/25] Current/Best: 13.10/ 21.09 GFLOPS | Progress: (16/20) | 11.19 s
+[Task 11/25] Current/Best: 19.43/ 21.56 GFLOPS | Progress: (20/20) | 13.30 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.77/ 18.06 GFLOPS | Progress: (4/20) | 5.81 s
-[Task 12/25] Current/Best: 5.30/ 18.06 GFLOPS | Progress: (8/20) | 9.75 s
-[Task 12/25] Current/Best: 18.81/ 19.02 GFLOPS | Progress: (12/20) | 11.73 s
-[Task 12/25] Current/Best: 15.42/ 19.02 GFLOPS | Progress: (16/20) | 14.69 s
-[Task 12/25] Current/Best: 15.14/ 19.02 GFLOPS | Progress: (20/20) | 16.63 s Done.
+[Task 12/25] Current/Best: 7.76/ 18.14 GFLOPS | Progress: (4/20) | 5.69 s
+[Task 12/25] Current/Best: 5.34/ 18.14 GFLOPS | Progress: (8/20) | 9.65 s
+[Task 12/25] Current/Best: 18.72/ 18.92 GFLOPS | Progress: (12/20) | 11.62 s
+[Task 12/25] Current/Best: 15.34/ 18.92 GFLOPS | Progress: (16/20) | 14.57 s
+[Task 12/25] Current/Best: 15.19/ 19.04 GFLOPS | Progress: (20/20) | 16.48 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.80/ 17.32 GFLOPS | Progress: (4/20) | 3.77 s
-[Task 13/25] Current/Best: 15.72/ 20.84 GFLOPS | Progress: (8/20) | 6.38 s
-[Task 13/25] Current/Best: 19.65/ 21.78 GFLOPS | Progress: (12/20) | 9.41 s
-[Task 13/25] Current/Best: 12.23/ 21.78 GFLOPS | Progress: (16/20) | 12.88 s
-[Task 13/25] Current/Best: 18.74/ 21.78 GFLOPS | Progress: (20/20) | 15.25 s Done.
+[Task 13/25] Current/Best: 8.75/ 17.32 GFLOPS | Progress: (4/20) | 3.74 s
+[Task 13/25] Current/Best: 15.69/ 21.16 GFLOPS | Progress: (8/20) | 6.35 s
+[Task 13/25] Current/Best: 19.60/ 21.85 GFLOPS | Progress: (12/20) | 9.33 s
+[Task 13/25] Current/Best: 12.27/ 21.85 GFLOPS | Progress: (16/20) | 12.77 s
+[Task 13/25] Current/Best: 18.30/ 21.85 GFLOPS | Progress: (20/20) | 15.07 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.56/ 13.56 GFLOPS | Progress: (4/20) | 3.45 s
-[Task 14/25] Current/Best: 6.08/ 13.56 GFLOPS | Progress: (8/20) | 5.68 s
-[Task 14/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (12/20) | 8.35 s
-[Task 14/25] Current/Best: 16.63/ 20.48 GFLOPS | Progress: (16/20) | 10.04 s Done.
+[Task 14/25] Current/Best: 12.54/ 13.24 GFLOPS | Progress: (4/20) | 3.41 s
+[Task 14/25] Current/Best: 6.12/ 13.36 GFLOPS | Progress: (8/20) | 5.55 s
+[Task 14/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (12/20) | 8.23 s
+[Task 14/25] Current/Best: 17.06/ 20.65 GFLOPS | Progress: (16/20) | 9.91 s Done.
-[Task 14/25] Current/Best: 17.33/ 20.48 GFLOPS | Progress: (20/20) | 11.78 s
+[Task 14/25] Current/Best: 17.20/ 20.65 GFLOPS | Progress: (20/20) | 11.65 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.16/ 17.66 GFLOPS | Progress: (4/20) | 2.74 s
-[Task 15/25] Current/Best: 14.31/ 18.09 GFLOPS | Progress: (8/20) | 4.08 s
-[Task 15/25] Current/Best: 10.39/ 22.25 GFLOPS | Progress: (12/20) | 6.36 s
-[Task 15/25] Current/Best: 20.37/ 22.25 GFLOPS | Progress: (16/20) | 9.53 s
-[Task 15/25] Current/Best: 9.69/ 22.25 GFLOPS | Progress: (20/20) | 10.55 s
+[Task 15/25] Current/Best: 16.02/ 17.60 GFLOPS | Progress: (4/20) | 2.71 s
+[Task 15/25] Current/Best: 14.45/ 18.01 GFLOPS | Progress: (8/20) | 4.05 s
+[Task 15/25] Current/Best: 10.39/ 22.20 GFLOPS | Progress: (12/20) | 6.30 s
+[Task 15/25] Current/Best: 20.42/ 22.20 GFLOPS | Progress: (16/20) | 9.36 s
+[Task 15/25] Current/Best: 9.69/ 22.20 GFLOPS | Progress: (20/20) | 10.37 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.31/ 20.31 GFLOPS | Progress: (4/20) | 2.96 s
-[Task 16/25] Current/Best: 3.04/ 20.31 GFLOPS | Progress: (8/20) | 4.60 s
-[Task 16/25] Current/Best: 19.71/ 20.31 GFLOPS | Progress: (12/20) | 5.83 s
-[Task 16/25] Current/Best: 17.23/ 20.31 GFLOPS | Progress: (16/20) | 7.20 s
-[Task 16/25] Current/Best: 10.01/ 21.77 GFLOPS | Progress: (20/20) | 9.38 s Done.
+[Task 16/25] Current/Best: 20.52/ 20.52 GFLOPS | Progress: (4/20) | 3.02 s
+[Task 16/25] Current/Best: 2.97/ 20.52 GFLOPS | Progress: (8/20) | 4.63 s
+[Task 16/25] Current/Best: 19.75/ 20.52 GFLOPS | Progress: (12/20) | 5.84 s
+[Task 16/25] Current/Best: 17.90/ 20.52 GFLOPS | Progress: (16/20) | 7.21 s
+[Task 16/25] Current/Best: 10.04/ 22.15 GFLOPS | Progress: (20/20) | 9.37 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.89/ 18.88 GFLOPS | Progress: (4/20) | 4.83 s
-[Task 17/25] Current/Best: 14.23/ 23.21 GFLOPS | Progress: (8/20) | 7.63 s
-[Task 17/25] Current/Best: 16.88/ 23.21 GFLOPS | Progress: (12/20) | 9.70 s
-[Task 17/25] Current/Best: 16.46/ 23.21 GFLOPS | Progress: (16/20) | 11.93 s
-[Task 17/25] Current/Best: 10.03/ 23.21 GFLOPS | Progress: (20/20) | 14.12 s Done.
+[Task 17/25] Current/Best: 12.79/ 18.65 GFLOPS | Progress: (4/20) | 4.81 s
+[Task 17/25] Current/Best: 14.42/ 23.44 GFLOPS | Progress: (8/20) | 7.58 s
+[Task 17/25] Current/Best: 16.94/ 23.44 GFLOPS | Progress: (12/20) | 9.66 s
+[Task 17/25] Current/Best: 16.50/ 23.44 GFLOPS | Progress: (16/20) | 11.93 s
+[Task 17/25] Current/Best: 10.00/ 23.44 GFLOPS | Progress: (20/20) | 14.09 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.12/ 18.19 GFLOPS | Progress: (4/20) | 3.86 s
-[Task 18/25] Current/Best: 10.55/ 18.60 GFLOPS | Progress: (8/20) | 7.56 s
-[Task 18/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (12/20) | 9.48 s
-[Task 18/25] Current/Best: 10.02/ 19.13 GFLOPS | Progress: (16/20) | 13.40 s
-[Task 18/25] Current/Best: 20.80/ 20.80 GFLOPS | Progress: (20/20) | 14.91 s Done.
+[Task 18/25] Current/Best: 11.19/ 18.13 GFLOPS | Progress: (4/20) | 3.82 s
+[Task 18/25] Current/Best: 10.58/ 20.13 GFLOPS | Progress: (8/20) | 7.51 s
+[Task 18/25] Current/Best: 19.36/ 20.13 GFLOPS | Progress: (12/20) | 9.43 s
+[Task 18/25] Current/Best: 10.01/ 20.13 GFLOPS | Progress: (16/20) | 13.30 s
+[Task 18/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (20/20) | 14.81 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.04/ 20.36 GFLOPS | Progress: (4/20) | 6.18 s
-[Task 19/25] Current/Best: 2.61/ 20.36 GFLOPS | Progress: (8/20) | 9.52 s
-[Task 19/25] Current/Best: 20.22/ 20.36 GFLOPS | Progress: (12/20) | 12.47 s
-[Task 19/25] Current/Best: 14.58/ 21.85 GFLOPS | Progress: (16/20) | 15.50 s
-[Task 19/25] Current/Best: 2.70/ 23.66 GFLOPS | Progress: (20/20) | 18.28 s Done.
+[Task 19/25] Current/Best: 7.16/ 20.17 GFLOPS | Progress: (4/20) | 6.09 s
+[Task 19/25] Current/Best: 2.61/ 20.17 GFLOPS | Progress: (8/20) | 9.40 s
+[Task 19/25] Current/Best: 19.34/ 20.86 GFLOPS | Progress: (12/20) | 12.38 s
+[Task 19/25] Current/Best: 14.12/ 21.41 GFLOPS | Progress: (16/20) | 15.39 s
+[Task 19/25] Current/Best: 2.70/ 23.51 GFLOPS | Progress: (20/20) | 18.19 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.03/ 15.53 GFLOPS | Progress: (4/20) | 3.31 s Done.
+[Task 20/25] Current/Best: 8.96/ 15.22 GFLOPS | Progress: (4/20) | 3.35 s Done.
Done.
-[Task 20/25] Current/Best: 9.77/ 15.53 GFLOPS | Progress: (8/20) | 6.82 s
-[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.74 s
-[Task 20/25] Current/Best: 12.26/ 16.60 GFLOPS | Progress: (16/20) | 14.50 s
-[Task 20/25] Current/Best: 10.87/ 22.04 GFLOPS | Progress: (20/20) | 16.61 s
+[Task 20/25] Current/Best: 9.82/ 15.22 GFLOPS | Progress: (8/20) | 6.89 s
+[Task 20/25] Current/Best: 2.32/ 16.47 GFLOPS | Progress: (12/20) | 10.86 s
+[Task 20/25] Current/Best: 12.59/ 16.47 GFLOPS | Progress: (16/20) | 14.64 s
+[Task 20/25] Current/Best: 12.49/ 22.01 GFLOPS | Progress: (20/20) | 16.79 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.41/ 17.75 GFLOPS | Progress: (4/20) | 3.28 s
-[Task 21/25] Current/Best: 14.66/ 17.75 GFLOPS | Progress: (8/20) | 4.89 s
-[Task 21/25] Current/Best: 1.61/ 17.75 GFLOPS | Progress: (12/20) | 7.01 s
-[Task 21/25] Current/Best: 17.69/ 17.75 GFLOPS | Progress: (16/20) | 10.53 s
-[Task 21/25] Current/Best: 4.47/ 17.75 GFLOPS | Progress: (20/20) | 17.88 s
+[Task 21/25] Current/Best: 6.39/ 17.70 GFLOPS | Progress: (4/20) | 3.29 s
+[Task 21/25] Current/Best: 14.66/ 17.70 GFLOPS | Progress: (8/20) | 4.88 s
+[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 7.02 s
+[Task 21/25] Current/Best: 18.03/ 18.03 GFLOPS | Progress: (16/20) | 10.55 s
+[Task 21/25] Current/Best: 4.47/ 18.03 GFLOPS | Progress: (20/20) | 17.95 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.96 GFLOPS | Progress: (4/20) | 2.68 s
-[Task 22/25] Current/Best: 8.76/ 21.57 GFLOPS | Progress: (8/20) | 4.73 s
-[Task 22/25] Current/Best: 19.89/ 21.57 GFLOPS | Progress: (12/20) | 7.09 s
-[Task 22/25] Current/Best: 15.48/ 21.57 GFLOPS | Progress: (16/20) | 9.24 s
-[Task 22/25] Current/Best: 14.56/ 21.57 GFLOPS | Progress: (20/20) | 10.91 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.98 GFLOPS | Progress: (4/20) | 2.69 s
+[Task 22/25] Current/Best: 9.07/ 21.93 GFLOPS | Progress: (8/20) | 4.72 s
+[Task 22/25] Current/Best: 19.93/ 21.93 GFLOPS | Progress: (12/20) | 7.11 s
+[Task 22/25] Current/Best: 15.28/ 21.93 GFLOPS | Progress: (16/20) | 9.23 s
+[Task 22/25] Current/Best: 14.29/ 21.93 GFLOPS | Progress: (20/20) | 10.98 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 16.15/ 20.35 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 23/25] Current/Best: 15.27/ 20.35 GFLOPS | Progress: (8/20) | 6.62 s
-[Task 23/25] Current/Best: 20.92/ 21.74 GFLOPS | Progress: (12/20) | 8.46 s
-[Task 23/25] Current/Best: 6.36/ 21.74 GFLOPS | Progress: (16/20) | 15.60 s
-[Task 23/25] Current/Best: 7.75/ 21.74 GFLOPS | Progress: (20/20) | 19.81 s Done.
+[Task 23/25] Current/Best: 17.55/ 20.67 GFLOPS | Progress: (4/20) | 3.24 s
+[Task 23/25] Current/Best: 14.86/ 20.67 GFLOPS | Progress: (8/20) | 6.61 s
+[Task 23/25] Current/Best: 20.94/ 21.85 GFLOPS | Progress: (12/20) | 8.46 s
+[Task 23/25] Current/Best: 6.47/ 21.85 GFLOPS | Progress: (16/20) | 15.55 s
+[Task 23/25] Current/Best: 7.88/ 21.85 GFLOPS | Progress: (20/20) | 19.76 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.82 s
-[Task 24/25] Current/Best: 2.14/ 8.58 GFLOPS | Progress: (8/20) | 22.82 s
-[Task 24/25] Current/Best: 4.54/ 8.58 GFLOPS | Progress: (12/20) | 34.35 s Done.
- Done.
+[Task 24/25] Current/Best: 8.63/ 8.63 GFLOPS | Progress: (4/20) | 11.78 s
+[Task 24/25] Current/Best: 3.49/ 8.63 GFLOPS | Progress: (8/20) | 23.01 s
+[Task 24/25] Current/Best: 4.57/ 8.63 GFLOPS | Progress: (12/20) | 33.74 s Done.
-[Task 24/25] Current/Best: 6.32/ 8.94 GFLOPS | Progress: (16/20) | 40.09 s
-[Task 24/25] Current/Best: 3.30/ 9.16 GFLOPS | Progress: (20/20) | 46.08 s Done.
+[Task 24/25] Current/Best: 7.06/ 8.86 GFLOPS | Progress: (16/20) | 39.45 s
+[Task 24/25] Current/Best: 3.39/ 8.87 GFLOPS | Progress: (20/20) | 45.44 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.77 GFLOPS | Progress: (4/20) | 11.61 s
-[Task 25/25] Current/Best: 5.93/ 8.10 GFLOPS | Progress: (8/20) | 22.89 s
-[Task 25/25] Current/Best: 6.01/ 8.10 GFLOPS | Progress: (12/20) | 34.34 s
-[Task 25/25] Current/Best: 5.89/ 8.86 GFLOPS | Progress: (16/20) | 36.24 s
-[Task 25/25] Current/Best: 2.85/ 8.86 GFLOPS | Progress: (20/20) | 46.93 s
+[Task 25/25] Current/Best: 1.55/ 2.80 GFLOPS | Progress: (4/20) | 11.59 s
+[Task 25/25] Current/Best: 5.66/ 7.91 GFLOPS | Progress: (8/20) | 22.86 s
+[Task 25/25] Current/Best: 5.87/ 7.91 GFLOPS | Progress: (12/20) | 34.26 s
+[Task 25/25] Current/Best: 5.77/ 9.73 GFLOPS | Progress: (16/20) | 36.15 s
+[Task 25/25] Current/Best: 2.86/ 9.73 GFLOPS | Progress: (20/20) | 46.82 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -919,7 +918,8 @@ model using optimized operators to speed up our computations.</p>
<a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="tvm.contrib.graph_executor.GraphModule" class="sphx-glr-backref-module-tvm-contrib-graph_executor sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">module</span></a> <span class="o">=</span> <a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="tvm.contrib.graph_executor.GraphModule" class="sphx-glr-backref-module-tvm-co [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Done.
+/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
</pre></div>
</div>
@@ -975,8 +975,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 406.3042897299965, 'median': 406.1970731999736, 'std': 0.8946138427652085}
-unoptimized: {'mean': 493.59745205998934, 'median': 493.46763434998593, 'std': 0.9481906503805504}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 411.43764090000786, 'median': 410.83044350000364, 'std': 1.5720975136900446}
+unoptimized: {'mean': 493.53625042998374, 'median': 493.4867044999919, 'std': 0.6957633864636172}
</pre></div>
</div>
</div>
@@ -990,7 +990,7 @@ 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> ( 10 minutes 24.011 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 25.530 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index c6a2be5f8..0a623520d 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -521,7 +521,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.26e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.274e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 87a9a2740..41c32e94e 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -478,7 +478,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x230601c0)), stage(b, placeholder(b, 0x2189e0d0)), 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=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x21009a60)), stage(b, placeholder(b, 0x23ea9590)), 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=[ [...]
</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 fbcccad1c..943314590 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:18.018</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:20.482</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,50 +331,50 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:24.011</p></td>
+<td><p>10:25.530</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.927</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
+<td><p>01:02.448</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:57.373</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
+<td><p>00:58.187</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:30.376</p></td>
+<td><p>00:29.645</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:23.665</p></td>
+<td><p>00:23.335</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.785</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.690</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.706</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.501</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.168</p></td>
+<td><p>00:00.140</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
+<tr class="row-odd"><td><p><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></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
+<tr class="row-even"><td><p><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></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 8c75f9471..f940dd41b 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -662,10 +662,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.334119997925882e-06 1.0
- naive 5.876399999999999e-06 0.7051014385996917
-parallel 6.1097e-06 0.7330947960337174
- vector 2.47353e-05 2.96795582570876
+ numpy 7.78187999912916e-06 1.0
+ naive 5.897e-06 0.7577860363639519
+parallel 6.1382e-06 0.7887811172476191
+ vector 2.4624099999999997e-05 3.164286779384363
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -981,7 +981,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019171
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018387
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1024,7 +1024,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.389451
+none: 3.216035
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1091,7 +1091,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.315025
+blocking: 0.304432
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1152,7 +1152,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.346574
+vectorization: 0.330172
@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], []),
@@ -1209,7 +1209,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.116758
+loop permutation: 0.117172
@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], []),
@@ -1287,7 +1287,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.108431
+array packing: 0.110589
@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], []),
@@ -1363,7 +1363,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.110439
+block caching: 0.110728
@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], []),
@@ -1432,7 +1432,7 @@ of thread-level parallelization.</p>
</div>
... 36 lines suppressed ...