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 2022/12/10 05:44:32 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@0dc26dd87052ca7c0245a9eb26110e83a96982b1)
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 5daa8afa92 deploying docs (apache/tvm@0dc26dd87052ca7c0245a9eb26110e83a96982b1)
5daa8afa92 is described below
commit 5daa8afa92a4da7f3f403db05f33cc7099e10281
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat Dec 10 05:44:26 2022 +0000
deploying docs (apache/tvm@0dc26dd87052ca7c0245a9eb26110e83a96982b1)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 327199 -> 332672 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22934 -> 24174 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2366 +++++++-------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 125 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 339 +--
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 13 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 49 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../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 | 34 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2366 +++++++-------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 125 +-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 339 +--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/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 | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 275 ++-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
129 files changed, 3087 insertions(+), 4214 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9acba7fd3b..3f59a37dab 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index fb0f49ab60..6746d44e45 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 4b79bb5fd6..1d949c775f 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.091 seconds)
+ **Total running time of the script:** ( 1 minutes 9.719 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index aefab5b8b8..fff65a4c12 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 965ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 977ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 0791b64c4a..c4724aba24 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.zip7597c36c-3b55-47ff-afa1-414479fd7846 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2bbcb9c0-7828-4717-8c9f-cbb479489188 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 3f18877e48..277b7636a4 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 51.3MB/s]
36%|###6 | 14.9M/41.5M [00:00<00:00, 61.4MB/s]
51%|#####1 | 21.3M/41.5M [00:00<00:00, 63.5MB/s]
66%|######6 | 27.5M/41.5M [00:00<00:00, 50.9MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 55.3MB/s]
96%|#########5| 39.7M/41.5M [00:00<00:00, 47.8MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 51.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 39.7MB/s]
36%|###5 | 14.9M/41.5M [00:00<00:00, 52.8MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.7MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.9MB/s]
93%|#########2| 38.4M/41.5M [00:00<00:00, 59.2MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 58.5MB/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 a7455ab5f3..ae0802c64d 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
21%|##1 | 9.55M/44.7M [00:00<00:00, 100MB/s]
43%|####2 | 19.1M/44.7M [00:00<00:00, 91.9MB/s]
62%|######2 | 27.9M/44.7M [00:00<00:00, 90.4MB/s]
82%|########1 | 36.5M/44.7M [00:00<00:00, 86.1MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 73.1MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
30%|##9 | 13.2M/44.7M [00:00<00:00, 135MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 113MB/s]
83%|########2 | 37.1M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 102MB/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 3d481d0df5..325f773036 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.679 seconds)
+ **Total running time of the script:** ( 1 minutes 13.403 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 e38a395774..fb04f73f5b 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
=================
-**05:41.355** total execution time for **how_to_compile_models** files:
+**05:49.430** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.679 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.403 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.091 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.719 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.712 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:48.304 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.789 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.878 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.717 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.640 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.011 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.350 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.561 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.470 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.232 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.861 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.154 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.361 | 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``) | 00:02.443 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index b61de62082..0540f913f8 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2756.7223 2755.7563 2764.4060 2754.1772 2.8380
+ 2757.3848 2756.3835 2761.8029 2755.1545 2.3504
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 714d1b3469..51a203ba9f 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
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6641 15.5366 16.7499 15.5040 0.3634
+ 16.5177 16.5123 17.3127 15.8657 0.4537
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 979be422da..24e33adaee 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:03, 55.1MB/s]
9%|8 | 14.5M/170M [00:00<00:02, 61.4MB/s]
12%|#2 | 20.5M/170M [00:00<00:03, 52.2MB/s]
15%|#5 | 25.6M/170M [00:00<00:03, 49.2MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 46.8MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 54.2MB/s]
28%|##8 | 48.1M/170M [00:00<00:02, 62.2MB/s]
32%|###1 | 54.3M/170M [00:01<00:02, 56.6MB/s]
35%|###5 | 59.9M/170M [00:01<00:02, 53.1MB/s]
39%|###8 | 66.0M/170M [00:01<00:01, 55.9MB/s]
42%|####2 | 72.0M/170M [00:01<00:02, 50.2MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 47.2MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 53.6MB/s]
56%|#####5 | 94.3M/170M [00:01<00:01, 54.1MB/s]
60%|###### | 102M/170M [00:01<00:01, 60.5MB/s]
64%|######3 | 108M/170M [00:02<00:01, 59.4MB/s]
67%|######7 | 114M/170M [00:02<00:00, 59.3MB/s]
72%|#######1 | 122M/170M [00:02<00:00, 65.9MB/s]
78%|#######8 | 133M/170M [00:02<00:00, 79.3MB/s]
83%|########2 | 141M/170M [00:02<00:00, 78.5MB/s]
87%|########7 | 148M/170M [00:02<00:00, 73.3MB/s]
94%|#########4| 160M/170M [00:02<00:00, 85.4MB/s]
99%|#########8| 168M/170M [00:02<00:00, 70.1MB/s]
100%|##########| 170M/170M [00:02<00:00, 61.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.57M/170M [00:00<00:02, 68.9MB/s]
8%|7 | 13.1M/170M [00:00<00:04, 39.0MB/s]
10%|# | 17.5M/170M [00:00<00:04, 33.6MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 39.9MB/s]
19%|#8 | 32.0M/170M [00:00<00:04, 33.4MB/s]
24%|##3 | 40.5M/170M [00:01<00:03, 44.5MB/s]
28%|##8 | 48.0M/170M [00:01<00:02, 51.8MB/s]
34%|###3 | 57.1M/170M [00:01<00:01, 62.3MB/s]
38%|###7 | 64.1M/170M [00:01<00:01, 60.4MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 55.2MB/s]
49%|####8 | 82.5M/170M [00:01<00:01, 67.9MB/s]
53%|#####2 | 89.7M/170M [00:01<00:01, 62.8MB/s]
59%|#####9 | 100M/170M [00:01<00:00, 74.3MB/s]
64%|######3 | 108M/170M [00:01<00:00, 74.9MB/s]
68%|######8 | 116M/170M [00:02<00:00, 70.5MB/s]
72%|#######2 | 123M/170M [00:02<00:00, 65.7MB/s]
76%|#######6 | 129M/170M [00:02<00:00, 56.6MB/s]
81%|######## | 137M/170M [00:02<00:00, 61.7MB/s]
85%|########4 | 144M/170M [00:02<00:00, 60.1MB/s]
91%|######### | 154M/170M [00:02<00:00, 72.2MB/s]
96%|#########5| 162M/170M [00:02<00:00, 75.2MB/s]
100%|#########9| 170M/170M [00:02<00:00, 71.1MB/s]
100%|##########| 170M/170M [00:02<00:00, 59.6MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 10.770 seconds)
+ **Total running time of the script:** ( 3 minutes 20.953 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 11d7054e16..f5a43f432f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 61.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 77.7MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 49.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 64.7MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3064 90.2467 92.4185 89.9342 0.3119
+ 90.3028 90.2496 91.1758 90.0903 0.1739
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.988 seconds)
+ **Total running time of the script:** ( 1 minutes 7.203 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 615405b23b..6201212165 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.1475 119.1158 121.0518 117.8614 0.5495
+ 120.6204 120.4145 125.5072 119.7050 0.8173
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 28.127 seconds)
+ **Total running time of the script:** ( 2 minutes 30.181 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 ad121c4a70..78961b5a37 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 29.041 seconds)
+ **Total running time of the script:** ( 1 minutes 29.307 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 9b82d4196f..d5ab42952a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6187/132723 [00:00<00:02, 61858.41KB/s]
11%|#1 | 14904/132723 [00:00<00:01, 76741.52KB/s]
18%|#7 | 23667/132723 [00:00<00:01, 81711.57KB/s]
24%|##4 | 32472/132723 [00:00<00:01, 84212.37KB/s]
31%|###1 | 41322/132723 [00:00<00:01, 85754.50KB/s]
38%|###7 | 50137/132723 [00:00<00:00, 86560.88KB/s]
44%|####4 | 58794/132723 [00:00<00:00, 86212.61KB/s]
51%|##### | 67664/132723 [00:00<00:00, 86999.16KB/s]
58%|#####7 | 76488/132723 [00:00<00:00, 87384.37KB/s]
64%|######4 | 85320/132723 [00:01<00:00, 87670.21KB/s]
71%|####### | 94088/132723 [00:01<00:00, 87598.90KB/s]
78%|#######7 | 102942/132723 [00:01<00:00, 87882.69KB/s]
84%|########4 | 111770/132723 [00:01<00:00, 87999.92KB/s]
91%|######### | 120623/132723 [00:01<00:00, 88157.66KB/s]
98%|#########7| 129465/132723 [00:01<00:00, 88233.43KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 86156.69KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6824/132723 [00:00<00:01, 68233.23KB/s]
12%|#1 | 15267/132723 [00:00<00:01, 77748.73KB/s]
17%|#7 | 23042/132723 [00:00<00:01, 76220.29KB/s]
24%|##3 | 31568/132723 [00:00<00:01, 79743.76KB/s]
30%|##9 | 39583/132723 [00:00<00:01, 79722.45KB/s]
36%|###5 | 47777/132723 [00:00<00:01, 80468.62KB/s]
42%|####2 | 56289/132723 [00:00<00:00, 81979.08KB/s]
49%|####8 | 64879/132723 [00:00<00:00, 83221.84KB/s]
55%|#####5 | 73457/132723 [00:00<00:00, 84015.96KB/s]
62%|######1 | 81920/132723 [00:01<00:00, 84201.93KB/s]
68%|######8 | 90478/132723 [00:01<00:00, 84621.66KB/s]
75%|#######4 | 99091/132723 [00:01<00:00, 85078.59KB/s]
81%|########1 | 107600/132723 [00:01<00:00, 85028.73KB/s]
88%|########7 | 116205/132723 [00:01<00:00, 85332.80KB/s]
94%|#########3| 124739/132723 [00:01<00:00, 85210.63KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 82922.55KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 2.381 seconds)
+ **Total running time of the script:** ( 3 minutes 9.149 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 e881b43a33..be2780b26f 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**13:33.991** total execution time for **how_to_deploy_models** files:
+**13:59.606** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:10.770 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:20.953 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:02.381 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:09.149 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.127 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.181 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:29.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:29.307 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:04.988 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.203 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.608 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.648 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.764 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.511 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.295 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.069 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.578 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index d8911826d7..78f20cf297 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip0b6fb6ef-1aeb-43c2-aa45-6d46452efb0c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip76c65472-fc65-49aa-a489-ce354f6179e2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 1fff9e5ce6..654632a065 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
=================
-**00:46.602** total execution time for **how_to_extend_tvm** files:
+**00:48.669** 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``) | 00:43.219 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.182 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.364 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.441 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.040 | 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 |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 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 a035a882e0..8c8c2fda3a 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: 7150us [7150us] (46.29%; 46.29%)
- FoldScaleAxis: 8296us [7us] (53.71%; 53.71%)
- FoldConstant: 8290us [1727us] (53.67%; 99.92%)
- InferType: 6563us [6563us] (42.49%; 79.17%)
+ InferType: 7219us [7219us] (46.78%; 46.78%)
+ FoldScaleAxis: 8212us [7us] (53.22%; 53.22%)
+ FoldConstant: 8205us [1646us] (53.18%; 99.92%)
+ InferType: 6559us [6559us] (42.51%; 79.94%)
@@ -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: 6553us [6553us] (44.83%; 44.83%)
- FoldScaleAxis: 8065us [5us] (55.17%; 55.17%)
- FoldConstant: 8061us [1661us] (55.14%; 99.94%)
- InferType: 6399us [6399us] (43.77%; 79.39%)
+ InferType: 6662us [6662us] (45.01%; 45.01%)
+ FoldScaleAxis: 8141us [5us] (54.99%; 54.99%)
+ FoldConstant: 8136us [1658us] (54.96%; 99.94%)
+ InferType: 6477us [6477us] (43.76%; 79.62%)
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 f2918079df..fef10b7c01 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: 33.136703 ms
+ Convolution: 43.125183 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 33f588c17d..1cc8084803 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
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.343097 ms
+ conv2d with tensor core: 12.843904 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 eceddbd917..254e1bdbb0 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: 0.017760
- Baseline: 3.483428
+ Numpy running time: 0.018469
+ Baseline: 3.462473
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.293434
+ Opt1: 0.303435
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.329534
+ Opt2: 0.342679
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114359
+ Opt3: 0.115973
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109011
+ Opt4: 0.108151
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110742
+ Opt5: 0.112048
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146781
+ Opt6: 0.147245
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 77fbe65723..2f0a82e6fc 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
=================
-**00:34.792** total execution time for **how_to_optimize_operators** files:
+**00:35.117** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.254 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.553 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.506 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.519 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.045 | 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 fb003c682a..403277af6d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:14.009** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:00.008** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:39.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:32.717 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.230 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.182 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.126 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.291 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:39.281 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.507 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.845 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.130 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.983 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.180 | 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 1e5063d8ff..c2eb0c79fb 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
@@ -239,11 +239,11 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -258,778 +258,463 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ for (rc.outer.outer: int32, 0, 64) {
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_2: int32 = (rc.outer.outer*72)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 161280)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 193536)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 225792)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4928), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5152), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5600), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5824), 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" = 224;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel_3[((((((blockIdx.x*294912) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 290304)]
- }
- for (ff.outer.inner: int32, 0, 2) {
- let cse_var_11: int32 = (ff.outer.inner*7)
- let cse_var_10: int32 = (cse_var_11 + 6)
- let cse_var_9: int32 = (cse_var_11 + 5)
- let cse_var_8: int32 = (cse_var_11 + 4)
- let cse_var_7: int32 = (cse_var_11 + 3)
- let cse_var_6: int32 = (cse_var_11 + 2)
- let cse_var_5: int32 = (cse_var_11 + 1)
- {
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 633)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 634)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 635)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 636)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 633)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 634)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 635)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 636)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 633)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 634)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 635)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 636)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 696)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 697)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 698)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 699)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 696)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 697)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 698)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 699)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 696)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 697)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 698)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 699)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 759)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 760)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 761)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 762)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 759)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 760)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 761)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 762)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 759)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 760)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 761)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 762)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 885)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 886)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 887)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 888)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 885)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 886)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 887)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 888)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 885)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 886)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 887)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 888)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 948)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 949)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 950)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 951)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 948)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 949)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 950)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 951)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 948)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 949)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 950)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 951)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1011)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1012)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1013)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1014)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1011)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1012)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1013)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1014)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1011)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1012)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1013)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1014)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1016)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1079)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1142)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1201)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1202)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1201)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1202)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1201)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1202)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1205)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1390)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1391)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1390)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1391)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1390)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1391)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1394)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1453)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1454)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1453)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1454)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1453)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1454)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1457)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1516)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1517)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1516)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1517)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1516)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1517)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1520)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1579)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1580)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1579)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1580)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1579)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1580)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1583)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1640)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1641)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1642)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1643)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1640)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1641)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1642)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1643)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1640)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1641)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1642)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1643)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1646)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1705)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1706)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1705)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1706)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1705)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1706)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1709)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1768)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1769)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1768)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1769)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1768)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1769)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1772)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1831)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1832)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1831)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1832)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1831)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1832)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1835)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1894)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1895)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1894)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1895)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1894)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1895)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1898)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1955)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1956)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1957)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1958)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1955)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1956)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1957)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1958)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1955)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1956)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1957)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1958)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1961)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
}
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
for (i1.inner: int32, 0, 2) {
for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1085,7 +770,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.428 ms
+ Execution time of this operator: 0.352 ms
@@ -1135,31 +820,31 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_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=32)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_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)
+ 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)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
@@ -1182,14 +867,14 @@ 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=224)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
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=224)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1207,10 +892,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[6144];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1225,728 +910,411 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 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) + 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) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 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) + 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) + 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) + 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) + 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) + 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) + 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);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 672)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 1344)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 2016)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 2688)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 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) + 3360)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 161280)];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 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) + 4032)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 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) + 4704)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 225792)];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4928) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5152) / 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) + 5376)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5600) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5824) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 96) {
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[((((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 290304)];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
}
- __syncthreads();
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1011)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1012)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1013)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1014)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1011)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1012)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1013)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1014)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1011)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1012)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1013)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1014)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1016)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1079)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1142)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1201)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1202)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1201)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1202)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1201)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1202)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1205)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1390)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1391)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1390)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1391)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1390)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1391)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1394)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1453)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1454)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1453)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1454)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1453)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1454)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1457)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1516)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1517)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1516)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1517)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1516)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1517)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1520)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1579)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1580)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1579)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1580)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1579)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1580)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1583)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1640)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1641)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1642)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1643)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1640)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1641)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1642)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1643)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1640)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1641)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1642)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1643)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1646)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1705)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1706)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1705)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1706)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1705)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1706)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1709)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1768)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1769)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1768)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1769)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1768)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1769)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1772)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1831)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1832)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1831)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1832)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1831)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1832)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1835)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1894)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1895)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1894)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1895)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1894)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1895)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1898)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1955)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1956)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1957)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1958)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1955)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1956)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1957)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1958)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1955)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1956)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1957)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1958)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1961)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -2009,7 +1377,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 39.545 seconds)
+ **Total running time of the script:** ( 5 minutes 32.717 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 117c774f2f..bc6a202b0f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8673 7.8628 7.8774 7.8617 0.0071
+ 7.8822 7.8840 7.8845 7.8781 0.0029
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.126 seconds)
+ **Total running time of the script:** ( 1 minutes 2.291 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index 69f470835e..bf3b9f2c59 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 749.7118 749.4310 752.3175 747.3870 2.0226
+ 783.9181 784.3521 784.7166 782.6856 0.8841
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.230 seconds)
+ **Total running time of the script:** ( 1 minutes 33.182 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 3b4b746254..21cd15dcab 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,14 +386,13 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer: int32, 0, 4) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- 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))
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
{
- compute_4: Buffer(compute_3, float32, [1024], [])[cse_var_1] = 0f32
+ compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
compute_4[(cse_var_1 + 1)] = 0f32
compute_4[(cse_var_1 + 2)] = 0f32
compute_4[(cse_var_1 + 3)] = 0f32
@@ -411,51 +410,81 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_4[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_19: int32 = ((i0.outer*8192) + (i.inner*256))
- let cse_var_18: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
{
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*128) + (i.inner*16))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_3]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*128) + (i.inner*16)) + 1)
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*128) + (i.inner*16)) + 2)
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*128) + (i.inner*16)) + 3)
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*128) + (i.inner*16)) + 4)
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*128) + (i.inner*16)) + 5)
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*128) + (i.inner*16)) + 6)
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*128) + (i.inner*16)) + 7)
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*128) + (i.inner*16)) + 8)
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*128) + (i.inner*16)) + 9)
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*128) + (i.inner*16)) + 10)
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*128) + (i.inner*16)) + 11)
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*128) + (i.inner*16)) + 12)
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*128) + (i.inner*16)) + 13)
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*128) + (i.inner*16)) + 14)
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*16)) + 15)
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_20, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -511,7 +540,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.779 ms
+ Execution time of this operator: 1.846 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 77a717610c..d764bc9474 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:24.122** total execution time for **how_to_tune_with_autotvm** files:
+**00:39.498** 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``) | 00:24.087 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:39.459 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.023 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.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 e0923a43e4..492c4d7289 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
@@ -387,7 +387,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,893513
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4644417
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -510,10 +510,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6803258
- No: 3 GFLOPS: 18.48/18.48 result: MeasureResult(costs=(0.012530515625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.823655366897583, timestamp=1670587331.8632438) [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6425064
- No: 4 GFLOPS: 77.10/77.10 result: MeasureResult(costs=(0.003002456411764706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7681941986083984, timestamp=1670587333.4850144) [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6595849
- No: 5 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,903192
+ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -635,8 +633,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4389549
- No: 6 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8540490
+ No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -758,8 +756,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,330947
- No: 7 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4724827
+ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -881,9 +879,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,302787
- No: 8 GFLOPS: 59.19/77.10 result: MeasureResult(costs=(0.0039114751,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9455833435058594, timestamp=1670587336.5763662) [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9297684
- No: 9 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7549074
+ No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1005,8 +1002,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,527802
- No: 10 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1135677
+ No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1128,8 +1125,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2926683
- No: 11 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7032174
+ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1251,8 +1248,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7508028
- No: 12 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 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,2824912
+ No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7010017
+ No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1374,8 +1389,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1773814
- No: 13 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6313242
+ No: 11 GFLOPS: 119.62/119.62 result: MeasureResult(costs=(0.0019353803461538465,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2919700145721436, timestamp=1670649520.2961972) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,265341
+ No: 12 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1497,8 +1513,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3793952
- No: 14 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2569313
+ No: 13 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1620,8 +1636,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,627215
- No: 15 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3029567
+ No: 14 GFLOPS: 17.61/119.62 result: MeasureResult(costs=(0.013147758444444444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1835360527038574, timestamp=1670649522.7851512) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1035992
+ No: 15 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1743,8 +1760,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7915996
- No: 16 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7932968
+ No: 16 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1866,131 +1883,161 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1077301
- No: 17 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1559113
+ No: 17 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+ During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f8228d11fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h:1617
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,280042
- No: 18 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
+
+ Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,778906
+ No: 18 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2112,8 +2159,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8470241
- No: 19 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1873653
+ No: 19 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2235,8 +2282,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('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, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3321273
- No: 20 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8099382
+ No: 20 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2358,7 +2405,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3079062
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4599615
@@ -2413,9 +2460,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6595849
+ [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,265341
Finish loading 20 records
- Time cost of this operator: 0.003391
+ Time cost of this operator: 0.001146
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 b12e040213..16f632b18e 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 311.6 98.723 (1, 2, 10, 10, 3) 2 1 [311.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.97 (1, 6, 10, 10) 1 1 [3.063]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.307 (1, 1, 10, 10, 3) 1 1 [0.969]
- Total_time - 315.632 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.3 98.73 (1, 2, 10, 10, 3) 2 1 [311.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.958 (1, 6, 10, 10) 1 1 [3.021]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.312 (1, 1, 10, 10, 3) 1 1 [0.983]
+ Total_time - 315.304 - - - - -
@@ -397,10 +397,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.4 97.49 (1, 6, 10, 10, 1) 2 1 [103.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.693 (1, 6, 10, 10) 1 1 [1.795]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.867 0.817 (1, 3, 10, 10, 1) 1 1 [0.867]
- Total_time - 106.062 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 136.2 98.108 (1, 6, 10, 10, 1) 2 1 [136.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.277 (1, 6, 10, 10) 1 1 [1.773]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.853 0.614 (1, 3, 10, 10, 1) 1 1 [0.853]
+ Total_time - 138.826 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index f8306547f5..6fb42367a9 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 18.1MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 28.2MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 51.0MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.099 seconds)
+ **Total running time of the script:** ( 1 minutes 4.132 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 7e2ab00dc6..b3b77e6dec 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/tmpgzkadn12/images/random'
+ '/tmp/tmprtqcm2s5/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpgzkadn12/images/target contains 8144 images
- /tmp/tmpgzkadn12/images/random contains 5000 images
+ /tmp/tmprtqcm2s5/images/target contains 8144 images
+ /tmp/tmprtqcm2s5/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 46s - loss: 0.2280 - accuracy: 0.9195 - val_loss: 0.1161 - val_accuracy: 0.9592 - 46s/epoch - 141ms/step
+ 328/328 - 47s - loss: 0.2191 - accuracy: 0.9222 - val_loss: 0.1461 - val_accuracy: 0.9532 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0994 - accuracy: 0.9630 - val_loss: 0.0944 - val_accuracy: 0.9679 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0951 - accuracy: 0.9648 - val_loss: 0.1402 - val_accuracy: 0.9573 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0676 - accuracy: 0.9740 - val_loss: 0.1067 - val_accuracy: 0.9675 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0672 - accuracy: 0.9764 - val_loss: 0.1104 - val_accuracy: 0.9626 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f6048763290>
+ <keras.callbacks.History object at 0x7f7d19fe6190>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 32.704 seconds)
+ **Total running time of the script:** ( 4 minutes 22.951 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 9373e52c21..b11bee8541 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:35.849** total execution time for **how_to_work_with_microtvm** files:
+**06:30.856** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:32.704 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:22.951 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:04.132 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.627 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:52.009 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.674 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.880 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.741 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.882 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 d4d02f6e0b..893159201e 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.245** total execution time for **how_to_work_with_relay** files:
+**00:45.978** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.174 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.420 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.402 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.766 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.661 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.785 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index d28b9bcb3f..c71a65dfb5 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 0x7f60475ec050>
+ <function my_cuda_math_rule at 0x7f7d1ac2a440>
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 bd2930df6e..047f6e999d 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:08.130** total execution time for **how_to_work_with_schedules** files:
+**00:08.863** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.681 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.242 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.108 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.241 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.574 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.594 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.567 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.031 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.023 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 8e1adbacf2..d1ef93ebfe 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_a64hl4d/input0.cc'\nsource_filename = \"/tmp/tmp_a64hl4d/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/tmpbjrmmd8z/input0.cc'\nsource_filename = \"/tmp/tmpbjrmmd8z/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 ef96774d57..471fb0fd70 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
=================
-**00:25.656** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.545** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.650 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.539 | 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 9774489340..0314c974da 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 28.03s!
+ resnet18_v1 inference graph built in 29.44s!
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 3c04e0955f..1ecbacdf94 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 19.07s!
+ yolov3-tiny inference graph built in 19.81s!
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 9204445387..9bab3b8e13 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
=================
-**01:38.933** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.851** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.952 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.477 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.981 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.374 | 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 8f578bd044..b09622e342 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.197** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.193** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.751 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.731 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.446 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.463 | 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 d0741d109c..4c36964dcc 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
=================
-**00:00.779** total execution time for **topic_vta_tutorials** files:
+**00:00.829** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.413 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.450 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.366 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.379 | 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 e4e9549754..6d1c2b9b89 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-
- *E
-
@@ -332,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.636 ms
+ Execution time of this operator: 95.081 ms
@@ -450,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 26.863 seconds)
+ **Total running time of the script:** ( 1 minutes 19.565 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 5653e75da2..635cc163a3 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 6.69/6.69 result: MeasureResult(costs=(0.0401401972,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8424115180969238, timestamp=1670585927.4977374) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
- No: 2 GFLOPS: 12.21/12.21 result: MeasureResult(costs=(0.021991216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4992499351501465, timestamp=1670585928.771169) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 3 GFLOPS: 2.49/12.21 result: MeasureResult(costs=(0.1079307244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8751695156097412, timestamp=1670585930.6623495) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
- No: 4 GFLOPS: 2.12/12.21 result: MeasureResult(costs=(0.12676794379999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.185821533203125, timestamp=1670585933.6123216) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
- No: 5 GFLOPS: 10.52/12.21 result: MeasureResult(costs=(0.025516373599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5842664241790771, timestamp=1670585934.3177726) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 6 GFLOPS: 3.13/12.21 result: MeasureResult(costs=(0.08562681999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5152649879455566, timestamp=1670585935.8512979) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
- No: 7 GFLOPS: 9.52/12.21 result: MeasureResult(costs=(0.028184653200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5922620296478271, timestamp=1670585937.2150228) [('tile_y', [-1, 2]), ('tile_x', [-1, 32])],None,51
- No: 8 GFLOPS: 13.65/13.65 result: MeasureResult(costs=(0.0196641954,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5076446533203125, timestamp=1670585937.733907) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
- No: 9 GFLOPS: 12.23/13.65 result: MeasureResult(costs=(0.0219534314,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4845156669616699, timestamp=1670585938.3309968) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
- No: 10 GFLOPS: 2.42/13.65 result: MeasureResult(costs=(0.11084956400000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8833634853363037, timestamp=1670585940.2678695) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 1 GFLOPS: 10.70/10.70 result: MeasureResult(costs=(0.025092665800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6306362152099609, timestamp=1670648061.367032) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 2 GFLOPS: 12.70/12.70 result: MeasureResult(costs=(0.021130825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5792088508605957, timestamp=1670648062.7237296) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
+ No: 3 GFLOPS: 0.51/12.70 result: MeasureResult(costs=(0.5265583504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.66336441040039, timestamp=1670648072.1707618) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+ No: 4 GFLOPS: 3.10/12.70 result: MeasureResult(costs=(0.086573559,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.599247932434082, timestamp=1670648073.8088725) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+ No: 5 GFLOPS: 12.73/12.73 result: MeasureResult(costs=(0.0210854202,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5678117275238037, timestamp=1670648074.521066) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
+ No: 6 GFLOPS: 2.98/12.73 result: MeasureResult(costs=(0.0899992324,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6895596981048584, timestamp=1670648076.9930506) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+ No: 7 GFLOPS: 1.54/12.73 result: MeasureResult(costs=(0.1742165688,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.008047342300415, timestamp=1670648080.0161426) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+ No: 8 GFLOPS: 9.43/12.73 result: MeasureResult(costs=(0.0284651478,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6851985454559326, timestamp=1670648080.7221723) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
+ No: 9 GFLOPS: 2.12/12.73 result: MeasureResult(costs=(0.12646463140000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.22455096244812, timestamp=1670648083.0735266) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
+ No: 10 GFLOPS: 4.03/12.73 result: MeasureResult(costs=(0.0666682966,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2770171165466309, timestamp=1670648084.3898952) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 7479582c42..994b3ce589 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 512.4454158000015, 'median': 513.0684038000027, 'std': 1.7376482493207308}
+ {'mean': 518.0747493000001, 'median': 517.0353156999965, 'std': 2.157673056936332}
@@ -554,31 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 9.89/ 14.55 GFLOPS | Progress: (4/20) | 11.38 s
[Task 1/25] Current/Best: 5.61/ 23.58 GFLOPS | Progress: (8/20) | 15.73 s
[Task 1/25] Current/Best: 12.73/ 23.58 GFLOPS | Progress: (12/20) | 18.17 s
[Task 1/25] Current/Best: 14.92/ 23.58 GFLOPS | Progress: (16/20) | 20.49 s
[Task 1/25] Current/Best: 15.05/ 23.58 GFLOPS | Progress: (20/20) | 23.15 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 5.08/ 18.91 GFLOPS | Progress: (4/20) | 2.64 s
[Task 2/25] Current/Best: 8.65/ 19.79 GFLOPS | Progress: (8/20) | 3.70 s
[Task 2/25] Current/Best: 5.95/ 19.79 GFLOPS | Progress: (12/20) | 5.43 s
[Task 2/25] Current/Best: 15.04/ 19.79 GFLOPS | Progress: (16/20) | 7.13 s
[Task 2/25] Current/Best: 7.03/ 19.79 GFLOPS | Progress: (20/20) | 9.06 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 11.91/ 19.82 GFLOPS | Progress: (4/20) | 3.34 s
[Task 3/25] Current/Best: 10.69/ 19.82 GFLOPS | Progress: (8/20) | 5.19 s
[Task 3/25] Current/Best: 6.25/ 19.82 GFLOPS | Progress: (12/20) | 7.36 s
[Task 3/25] Current/Best: 17.79/ 19.82 GFLOPS | Progress: (16/20) | 9.07 s
[Task 3/25] Current/Best: 11.56/ 19.82 GFLOPS | Progress: (20/20) | 11.19 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 8.16/ 16.83 GFLOPS | Progress: (4/20) | 4.02 s
[Task 4/25] Current/Best: 12.76/ 16.83 GFLOPS | Progress: (8/20) | 5.47 s
[Task 4/25] Current/Best: 6.55/ 22.60 GFLOPS | Progress: (12/20) | 8.02 s
[Task 4/25] Current/Best: 15.51/ 22.60 GFLOPS | Progress: (16/20) | 12.16 s
[Task 4/25] Current/Best: 15.39/ 22.60 GFLOPS | Progress: (20/20) | 14.84 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 3.58/ 14.95 GFLOPS | Progress: (4/20) | 3.20 s
[Task 5/25] Current/Best: 14.70/ 20.71 GFLOPS | Progress: (8/20) | 4.51 s
[Task 5/25] Current/Best: 11.80/ 20.71 GFLOPS | Progress: (12/20) | 6.62 s
[Task 5/25] Current/Best: 20.17/ 20.71 GFLOPS | Progress: (16/20) | 8.22 s
[Task 5/25] Current/Best: 9.83/ 20.71 GFLOPS | Progress: (20/20) | 10.17 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 20.84/ 20.84 GFLOPS | Progress: (4/20) | 4.40 s
[Task 6/25] Current/Best: 15.07/ 20.84 GFLOPS | Progress: (8/20) | 7.60 s
[Task 6/25] Current/Best: 20.41/ 20.84 GFLOPS | Progress: (12/20) | 9.20 s
[Task 6/25] Current/Best: 20.69/ 20.84 GFLOPS | Progress: (16/20) | 11.65 s
[Task 6/25] Current/Best: 12.59/ 20.84 GFLOPS | Progress: (20/20) | 14.10 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 22.00/ 22.00 GFLOPS | Progress: (4/20) | 3.84 s
[Task 7/25] Current/Best: 18.87/ 22.00 GFLOPS | Progress: (8/20) | 5.84 s
[Task 7/25] Current/Best: 18.23/ 22.00 GFLOPS | Progress: (12/20) | 8.05 s
[Task 7/25] Current/Best: 11.46/ 22.00 GFLOPS | Progress: (16/20) | 10.06 s
[Task 7/25] Current/Best: 15.30/ 22.00 GFLOPS | Progress: (20/20) | 12.67 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/ 12.17 GFLOPS | Progress: (4/20) | 11.02 s
[Task 8/25] Current/Best: 14.36/ 15.79 GFLOPS | Progress: (8/20) | 13.21 s
[Task 8/25] Current/Best: 11.64/ 15.79 GFLOPS | Progress: (12/20) | 24.61 s
[Task 8/25] Current/Best: 8.40/ 15.79 GFLOPS | Progress: (16/20) | 27.60 s
[Task 8/25] Current/Best: 14.01/ 15.79 GFLOPS | Progress: (20/20) | 30.11 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 18.12/ 21.80 GFLOPS | Progress: (4/20) | 8.72 s
[Task 9/25] Current/Best: 20.39/ 21.80 GFLOPS | Progress: (8/20) | 10.24 s
[Task 9/25] Current/Best: 7.67/ 21.80 GFLOPS | Progress: (12/20) | 21.19 s
[Task 9/25] Current/Best: 13.92/ 21.80 GFLOPS | Progress: (16/20) | 24.45 s
[Task 9/25] Current/Best: 9.16/ 21.80 GFLOPS | Progress: (20
/20) | 29.99 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 8.96/ 15.60 GFLOPS | Progress: (4/20) | 3.43 s
[Task 10/25] Current/Best: 15.26/ 15.60 GFLOPS | Progress: (8/20) | 5.19 s
[Task 10/25] Current/Best: 20.39/ 20.39 GFLOPS | Progress: (12/20) | 6.84 s
[Task 10/25] Current/Best: 11.79/ 20.39 GFLOPS | Progress: (16/20) | 9.35 s
[Task 10/25] Current/Best: 14.95/ 20.84 GFLOPS | Progress: (20/20) | 11.70 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 15.55/ 15.55 GFLOPS | Progress: (4/20) | 3.65 s
[Task 11/25] Current/Best: 12.34/ 22.70 GFLOPS | Progress: (8/20) | 6.71 s
[Task 11/25] Current/Best: 16.66/ 23.59 GFLOPS | Progress: (12/20) | 8.59 s
[Task 11/25] Current/Best: 12.26/ 23.59 GFLOPS | Progress: (16/20) | 11.37 s
[Task 11/25] Current/Best: 7.80/ 23.59 GFLOPS | Progress: (20/20) | 14.31 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 5.09/ 18.75 GFLOPS | Progress: (4/20) | 6.85 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 5.66/ 16.42 GFLOPS | Progress: (4/20) | 10.00 s
[Task 1/25] Current/Best: 16.89/ 19.25 GFLOPS | Progress: (8/20) | 13.75 s
[Task 1/25] Current/Best: 10.89/ 22.13 GFLOPS | Progress: (12/20) | 16.72 s
[Task 1/25] Current/Best: 22.27/ 22.27 GFLOPS | Progress: (16/20) | 19.36 s
[Task 1/25] Current/Best: 12.75/ 22.27 GFLOPS | Progress: (20/20) | 21.54 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 20.89/ 21.61 GFLOPS | Progress: (4/20) | 3.16 s
[Task 2/25] Current/Best: 15.45/ 21.61 GFLOPS | Progress: (8/20) | 4.50 s
[Task 2/25] Current/Best: 6.97/ 21.61 GFLOPS | Progress: (12/20) | 6.48 s
[Task 2/25] Current/Best: 7.18/ 21.61 GFLOPS | Progress: (16/20) | 7.93 s
[Task 2/25] Current/Best: 15.58/ 21.61 GFLOPS | Progress: (20/20) | 9.79 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 22.95/ 22.95 GFLOPS | Progress: (4/20) | 4.16 s
[Task 3/25] Current/Best: 6.06/ 22.95 GFLOPS | Progress: (8/20) | 6.66 s
[Task 3/25] Current/Best: 11.40/ 22.95 GFLOPS | Progress: (12/20) | 9.68 s
[Task 3/25] Current/Best: 15.65/ 22.95 GFLOPS | Progress: (16/20) | 12.10 s
[Task 3/25] Current/Best: 16.57/ 22.95 GFLOPS | Progress: (20/20) | 13.92 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/ 13.70 GFLOPS | Progress: (4/20) | 5.51 s
[Task 4/25] Current/Best: 17.16/ 19.96 GFLOPS | Progress: (8/20) | 7.25 s
[Task 4/25] Current/Best: 18.41/ 19.96 GFLOPS | Progress: (12/20) | 9.28 s
[Task 4/25] Current/Best: 4.21/ 19.96 GFLOPS | Progress: (16/20) | 11.66 s
[Task 4/25] Current/Best: 11.61/ 21.08 GFLOPS | Progress: (20/20) | 17.41 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (4/20) | 4.19 s
[Task 5/25] Current/Best: 12.32/ 19.21 GFLOPS | Progress: (8/20) | 6.43 s
[Task 5/25] Current/Best: 15.14/ 19.21 GFLOPS | Progress: (12/20) | 8.36 s
[Task 5/25] Current/Best: 11.51/ 19.21 GFLOPS | Progress: (16/20) | 10.41 s
[Task 5/25] Current/Best: 19.03/ 19.21 GFLOPS | Progress: (20/20) | 12.59 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 16.19/ 16.19 GFLOPS | Progress: (4/20) | 5.27 s
[Task 6/25] Current/Best: 11.19/ 17.76 GFLOPS | Progress: (8/20) | 9.11 s
[Task 6/25] Current/Best: 13.99/ 17.76 GFLOPS | Progress: (12/20) | 14.64 s
[Task 6/25] Current/Best: 21.25/ 21.25 GFLOPS | Progress: (16/20) | 22.20 s
[Task 6/25] Current/Best: 19.98/ 21.25 GFLOPS | Progress: (20/20) | 24.61 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.46/ 18.11 GFLOPS | Progress: (4/20) | 4.54 s
[Task 7/25] Current/Best: 8.46/ 21.04 GFLOPS | Progress: (8/20) | 6.83 s
[Task 7/25] Current/Best: 12.60/ 21.04 GFLOPS | Progress: (12/20) | 9.31 s
[Task 7/25] Current/Best: 6.65/ 21.04 GFLOPS | Progress: (16/20) | 12.87 s
[Task 7/25] Current/Best: 8.89/ 21.04 GFLOPS | Progress: (20/20) | 16.13 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.33/ 13.39 GFLOPS | Progress: (4/20) | 10.32 s
[Task 8/25] Current/Best: 11.28/ 18.95 GFLOPS | Progress: (8/20) | 13.40 s
[Task 8/25] Current/Best: 7.40/ 20.00 GFLOPS | Progress: (12/20) | 18.12 s
[Task 8/25] Current/Best: 8.24/ 20.00 GFLOPS | Progress: (16/20) | 26.77 s
[Task 8/25] Current/Best: 12.47/ 20.00 GFLOPS | Progress: (20/20) | 29.71 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 6.96/ 17.88 GFLOPS | Progress: (4/20) | 13.10 s
[Task 9/25] Current/Best: 6.40/ 17.88 GFLOPS | Progress: (8/20) | 16.48 s
[Task 9/25] Current/Best: 6.38/ 20.70 GFLOPS | Progress: (12/20) | 18.36 s
[Task 9/25] Current/Best: 3.14/ 20.70 GFLOPS | Progress: (16/20) | 21.45 s
[Task 9/25] Current/Best: 6.05/ 20.70 GFLOPS | Progress: (20/20) | 30.38 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 17.65/ 17.65 GFLOPS | Progress: (4/20) | 3.88 s
[Task 10/25] Current/Best: 12.78/ 21.72 GFLOPS | Progress: (8/20) | 6.20 s
[Task 10/25] Current/Best: 10.02/ 21.72 GFLOPS | Progress: (12/20) | 9.38 s
[Task 10/25] Current/Best: 5.23/ 21.72 GFLOPS | Progress: (16/20) | 11.61 s
[Task 10/25] Current/Best: 3.19/ 21.72 GFLOPS | Progress: (20/2
0) | 13.99 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 19.94/ 19.94 GFLOPS | Progress: (4/20) | 3.88 s
[Task 11/25] Current/Best: 8.76/ 20.11 GFLOPS | Progress: (8/20) | 6.55 s
[Task 11/25] Current/Best: 1.58/ 21.80 GFLOPS | Progress: (12/20) | 11.83 s
[Task 11/25] Current/Best: 11.60/ 21.80 GFLOPS | Progress: (16/20) | 15.13 s
[Task 11/25] Current/Best: 5.08/ 21.80 GFLOPS | Progress: (20/20) | 18.01 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.87/ 14.20 GFLOPS | Progress: (4/20) | 8.50 s
[Task 12/25] Current/Best: 8.64/ 16.82 GFLOPS | Progress: (8/20) | 11.26 s
[Task 12/25] Current/Best: 11.87/ 16.82 GFLOPS | Progress: (12/20) | 15.11 s
[Task 12/25] Current/Best: 14.63/ 16.82 GFLOPS | Progress: (16/20) | 17.45 s
[Task 12/25] Current/Best: 11.14/ 16.82 GFLOPS | Progress: (20/20) | 20.03 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (4/20) | 5.21 s
[Task 13/25] Current/Best: 12.18/ 18.09 GFLOPS | Progress: (8/20) | 8.58 s
[Task 13/25] Current/Best: 17.94/ 18.09 GFLOPS | Progress: (12/20) | 11.86 s
[Task 13/25] Current/Best: 18.47/ 18.47 GFLOPS | Progress: (16/20) | 14.20 s
[Task 13/25] Current/Best: 18.28/ 21.64 GFLOPS | Progress: (20/20) | 17.47 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.71/ 18.12 GFLOPS | Progress: (4/20) | 4.76 s
[Task 14/25] Current/Best: 10.89/ 18.12 GFLOPS | Progress: (8/20) | 12.78 s
[Task 14/25] Current/Best: 14.06/ 18.12 GFLOPS | Progress: (12/20) | 16.11 s
[Task 14/25] Current/Best: 15.78/ 19.73 GFLOPS | Progress: (16/20) | 17.91 s
[Task 14/25] Current/Best: 8.61/ 19.73 GFLOPS | Progress: (20/20) | 22.79 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 18.01/ 18.16 GFLOPS | Progress: (4/20) | 3.43 s Done.
Done.
-
[Task 12/25] Current/Best: 11.76/ 18.75 GFLOPS | Progress: (8/20) | 12.82 s
[Task 12/25] Current/Best: 8.29/ 18.75 GFLOPS | Progress: (12/20) | 16.20 s
[Task 12/25] Current/Best: 16.49/ 21.26 GFLOPS | Progress: (16/20) | 17.95 s
[Task 12/25] Current/Best: 10.63/ 21.26 GFLOPS | Progress: (20/20) | 20.91 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.70/ 21.93 GFLOPS | Progress: (4/20) | 5.39 s
[Task 13/25] Current/Best: 17.06/ 21.93 GFLOPS | Progress: (8/20) | 7.23 s
[Task 13/25] Current/Best: 17.87/ 21.93 GFLOPS | Progress: (12/20) | 11.28 s
[Task 13/25] Current/Best: 12.42/ 21.93 GFLOPS | Progress: (16/20) | 13.17 s
[Task 13/25] Current/Best: 6.21/ 21.93 GFLOPS | Progress: (20/20) | 15.30 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 18.36/ 18.36 GFLOPS | Progress: (4/20) | 4.37 s
[Task 14/25] Current/Best: 5.85/ 18.36 GFLOPS | Progress: (8/20) | 7.74 s
[Task 14/25] Current/Best: 14.62/ 20.81 GFLOPS | Progress: (12/20) | 10.09 s
[Task 14/25] Current/Best: 9.08/ 20.81 GFLOPS | Progress: (16/20) | 16.43 s
[Task 14/25] Current/Best: 22.52/ 22.52 GFLOPS | Progress: (20/20) | 21.86 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.44/ 15.54 GFLOPS | Progress: (4/20) | 4.42 s
[Task 15/25] Current/Best: 11.75/ 15.54 GFLOPS | Progress: (8/20) | 6.14 s
[Task 15/25] Current/Best: 8.82/ 15.91 GFLOPS | Progress: (12/20) | 8.25 s
[Task 15/25] Current/Best: 17.38/ 23.01 GFLOPS | Progress: (16/20) | 9.99 s
[Task 15/25] Current/Best: 9.01/ 23.01 GFLOPS | Progress: (20/20)
| 11.74 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 16/25] Current/Best: 9.44/ 16.12 GFLOPS | Progress: (4/20) | 3.55 s
[Task 16/25] Current/Best: 16.04/ 22.45 GFLOPS | Progress: (8/20) | 5.01 s
[Task 16/25] Current/Best: 14.86/ 22.45 GFLOPS | Progress: (12/20) | 8.06 s
[Task 16/25] Current/Best: 12.65/ 22.45 GFLOPS | Progress: (16/20) | 10.72 s
[Task 16/25] Current/Best: 11.18/ 22.45 GFLOPS | Progress: (20/20) | 12.85 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.57/ 12.27 GFLOPS | Progress: (4/20) | 3.91 s
[Task 17/25] Current/Best: 6.06/ 15.84 GFLOPS | Progress: (8/20) | 6.66 s
[Task 17/25] Current/Best: 18.33/ 18.42 GFLOPS | Progress: (12/20) | 8.92 s
[Task 17/25] Current/Best: 14.60/ 19.36 GFLOPS | Progress: (16/20) | 11.10 s
[Task 17/25] Current/Best: 6.16/ 19.36 GFLOPS | Progress: (20/20) | 15.17 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 16.08/ 20.72 GFLOPS | Progress: (4/20) | 5.11 s
[Task 18/25] Current/Best: 3.85/ 20.72 GFLOPS | Progress: (8/20) | 8.06 s
[Task 18/25] Current/Best: 5.07/ 20.72 GFLOPS | Progress: (12/20) | 10.64 s
[Task 18/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (16/20) | 12.37 s
[Task 18/25] Current/Best: 2.99/ 21.19 GFLOPS | Progress: (20/20) | 16.33 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.04/ 21.09 GFLOPS | Progress: (4/20) | 4.50 s
[Task 19/25] Current/Best: 2.69/ 21.09 GFLOPS | Progress: (8/20) | 9.54 s
[Task 19/25] Current/Best: 11.93/ 21.09 GFLOPS | Progress: (12/20) | 12.63 s
[Task 19/25] Current/Best: 16.81/ 21.09 GFLOPS | Progress: (16/20) | 15.70 s
[Task 19/25] Current/Best: 16.39/ 21.09 GFLOPS | Progress: (20/20) | 18.78 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 15.87/ 16.51 GFLOPS | Progress: (4/20) | 4.37 s
[Task 20/25] Current/Best: 7.59/ 16.51 GFLOPS | Progress: (8/20) | 6.66 s
[Task 20/25] Current/Best: 9.22/ 20.85 GFLOPS | Progress: (12/20) | 9.86 s
[Task 20/25] Current/Best: 14.27/ 20.85 GFLOPS | Progress: (16/20) | 12.91 s
[Task 20/25] Current/Best: 1.58/ 20.85 GFLOPS | Progress: (20/20) | 15.81 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.32/ 19.49 GFLOPS | Progress: (4/20) | 3.34 s
[Task 21/25] Current/Best: 14.38/ 20.97 GFLOPS | Progress: (8/20) | 6.50 s
[Task 21/25] Current/Best: 9.37/ 21.74 GFLOPS | Progress: (12/20) | 8.56 s
[Task 21/25] Current/Best: 16.36/ 21.74 GFLOPS | Progress: (16/20) | 9.86 s
[Task 21/25] Current/Best: 8.53/ 21.74 GFLOPS | Progress: (20/20) |
13.56 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 22/25] Current/Best: 16.87/ 18.85 GFLOPS | Progress: (4/20) | 3.56 s
[Task 22/25] Current/Best: 19.48/ 19.48 GFLOPS | Progress: (8/20) | 5.31 s
[Task 22/25] Current/Best: 6.70/ 19.48 GFLOPS | Progress: (12/20) | 7.19 s
[Task 22/25] Current/Best: 14.70/ 19.48 GFLOPS | Progress: (16/20) | 9.50 s
[Task 22/25] Current/Best: 19.31/ 20.94 GFLOPS | Progress: (20/20) | 10.68 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 12.09/ 12.09 GFLOPS | Progress: (4/20) | 4.92 s
[Task 23/25] Current/Best: 19.79/ 19.79 GFLOPS | Progress: (8/20) | 8.22 s
[Task 23/25] Current/Best: 17.56/ 19.79 GFLOPS | Progress: (12/20) | 11.75 s
[Task 23/25] Current/Best: 10.65/ 19.79 GFLOPS | Progress: (16/20) | 20.17 s
[Task 23/25] Current/Best: 21.75/ 21.75 GFLOPS | Progress: (20/20) | 22.54 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.20/ 9.20 GFLOPS | Progress: (4/20) | 12.22 s
[Task 24/25] Current/Best: 2.88/ 10.33 GFLOPS | Progress: (8/20) | 22.88 s
[Task 24/25] Current/Best: 1.55/ 10.33 GFLOPS | Progress: (12/20) | 33.91 s
[Task 24/25] Current/Best: 6.00/ 10.33 GFLOPS | Progress: (16/20) | 44.62 s
[Task 24/25] Current/Best: 1.45/ 10.33 GFLOPS | Progress: (20/20) | 55.34 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 4.37/ 5.75 GFLOPS | Progress: (4/20) | 3.44 s
[Task 25/25] Current/Best: 9.70/ 9.70 GFLOPS | Progress: (8/20) | 11.50 s
[Task 25/25] Current/Best: 4.11/ 9.70 GFLOPS | Progress: (12/20) | 22.23 s
[Task 25/25] Current/Best: 1.55/ 9.70 GFLOPS | Progress: (16/20) | 32.97 s
[Task 25/25] Current/Best: 1.55/ 9.70 GFLOPS | Progress: (20/20) | 43.47 s
+
[Task 15/25] Current/Best: 17.52/ 18.16 GFLOPS | Progress: (8/20) | 7.57 s
[Task 15/25] Current/Best: 8.68/ 22.75 GFLOPS | Progress: (12/20) | 9.21 s
[Task 15/25] Current/Best: 12.06/ 22.75 GFLOPS | Progress: (16/20) | 11.35 s
[Task 15/25] Current/Best: 3.10/ 22.75 GFLOPS | Progress: (20/20) | 13.40 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.27/ 20.84 GFLOPS | Progress: (4/20) | 3.53 s
[Task 16/25] Current/Best: 12.31/ 20.84 GFLOPS | Progress: (8/20) | 5.61 s
[Task 16/25] Current/Best: 10.11/ 20.84 GFLOPS | Progress: (12/20) | 9.06 s
[Task 16/25] Current/Best: 19.55/ 20.84 GFLOPS | Progress: (16/20) | 11.34 s
[Task 16/25] Current/Best: 12.56/ 20.84 GFLOPS | Progress: (20/20) | 13.14 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.74/ 18.01 GFLOPS | Progress: (4/20) | 5.11 s
[Task 17/25] Current/Best: 21.40/ 21.40 GFLOPS | Progress: (8/20) | 8.58 s
[Task 17/25] Current/Best: 15.20/ 21.40 GFLOPS | Progress: (12/20) | 11.91 s
[Task 17/25] Current/Best: 12.11/ 21.40 GFLOPS | Progress: (16/20) | 15.23 s
[Task 17/25] Current/Best: 11.15/ 21.40 GFLOPS | Progress: (20/20) | 18.35 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 6.48/ 19.08 GFLOPS | Progress: (4/20) | 4.07 s
[Task 18/25] Current/Best: 14.26/ 19.08 GFLOPS | Progress: (8/20) | 6.42 s
[Task 18/25] Current/Best: 7.10/ 19.08 GFLOPS | Progress: (12/20) | 10.08 s
[Task 18/25] Current/Best: 4.81/ 19.14 GFLOPS | Progress: (16/20) | 12.44 s
[Task 18/25] Current/Best: 4.94/ 19.14 GFLOPS | Progress: (20/20) | 14.92 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.07/ 21.07 GFLOPS | Progress: (4/20) | 4.18 s
[Task 19/25] Current/Best: 7.30/ 21.07 GFLOPS | Progress: (8/20) | 8.34 s
[Task 19/25] Current/Best: 5.31/ 21.07 GFLOPS | Progress: (12/20) | 11.18 s
[Task 19/25] Current/Best: 14.27/ 21.07 GFLOPS | Progress: (16/20) | 13.79 s
[Task 19/25] Current/Best: 16.21/ 21.07 GFLOPS | Progress: (20/20) | 20.23 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 7.04/ 18.75 GFLOPS | Progress: (4/20) | 5.68 s
[Task 20/25] Current/Best: 22.17/ 22.17 GFLOPS | Progress: (8/20) | 7.61 s
[Task 20/25] Current/Best: 10.15/ 22.17 GFLOPS | Progress: (12/20) | 11.21 s
[Task 20/25] Current/Best: 13.61/ 22.17 GFLOPS | Progress: (16/20) | 13.36 s
[Task 20/25] Current/Best: 17.66/ 22.17 GFLOPS | Progress: (20/20) | 16.12 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 4.15/ 14.36 GFLOPS | Progress: (4/20) | 6.77 s
[Task 21/25] Current/Best: 10.68/ 14.36 GFLOPS | Progress: (8/20) | 8.57 s Done.
+
[Task 21/25] Current/Best: 19.75/ 19.75 GFLOPS | Progress: (12/20) | 10.83 s
[Task 21/25] Current/Best: 17.13/ 19.75 GFLOPS | Progress: (16/20) | 14.16 s
[Task 21/25] Current/Best: 9.80/ 19.75 GFLOPS | Progress: (20/20) | 16.35 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.47/ 11.27 GFLOPS | Progress: (4/20) | 4.65 s
[Task 22/25] Current/Best: 11.88/ 18.59 GFLOPS | Progress: (8/20) | 6.92 s
[Task 22/25] Current/Best: 16.55/ 18.59 GFLOPS | Progress: (12/20) | 8.82 s
[Task 22/25] Current/Best: 13.98/ 18.59 GFLOPS | Progress: (16/20) | 10.63 s
[Task 22/25] Current/Best: 10.53/ 18.59 GFLOPS | Progress: (20/20) | 13.29 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 18.61/ 18.61 GFLOPS | Progress: (4/20) | 4.89 s
[Task 23/25] Current/Best: 6.13/ 21.64 GFLOPS | Progress: (8/20) | 7.48 s
[Task 23/25] Current/Best: 12.32/ 21.64 GFLOPS | Progress: (12/20) | 10.73 s
[Task 23/25] Current/Best: 10.55/ 21.64 GFLOPS | Progress: (16/20) | 13.33 s
[Task 23/25] Current/Best: 6.37/ 21.64 GFLOPS | Progress: (20/20) | 18.64 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.52/ 5.45 GFLOPS | Progress: (4/20) | 12.78 s
[Task 24/25] Current/Best: 5.61/ 5.61 GFLOPS | Progress: (8/20) | 24.29 s
[Task 24/25] Current/Best: 8.57/ 8.57 GFLOPS | Progress: (12/20) | 35.21 s
[Task 24/25] Current/Best: 5.68/ 8.57 GFLOPS | Progress: (16/20) | 46.16 s
[Task 24/25] Current/Best: 6.52/ 10.16 GFLOPS | Progress: (20/20) | 48.37 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 7.54/ 7.54 GFLOPS | Progress: (4/20) | 12.77 s
[Task 25/25] Current/Best: 1.56/ 7.54 GFLOPS | Progress: (8/20) | 23.72 s
[Task 25/25] Current/Best: 3.60/ 7.54 GFLOPS | Progress: (12/20) | 35.51 s
[Task 25/25] Current/Best: 1.55/ 8.31 GFLOPS | Progress: (16/20) | 46.48 s
[Task 25/25] Current/Best: 1.55/ 8.31 GFLOPS | Progress: (20/20) | 48.70 s Done.
+
@@ -675,7 +675,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356379
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 402.3451420000015, 'median': 401.9984273499972, 'std': 2.329275914806417}
- unoptimized: {'mean': 512.4454158000015, 'median': 513.0684038000027, 'std': 1.7376482493207308}
+ optimized: {'mean': 402.38666070000136, 'median': 402.0398830499971, 'std': 2.9881840266733635}
+ unoptimized: {'mean': 518.0747493000001, 'median': 517.0353156999965, 'std': 2.157673056936332}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 20.437 seconds)
+ **Total running time of the script:** ( 12 minutes 0.294 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 496d9491a9..002def568d 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.29e-07 secs/op
+ 1.289e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 73a284bbeb..6214bbf6d7 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x4396b40)), stage(b, placeholder(b, 0xa0ffa90)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+ [stage(a, placeholder(a, 0x20ef7ca0)), stage(b, placeholder(b, 0x20bd80b0)), 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 d60c8234ec..957033f16f 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:42.164** total execution time for **tutorial** files:
+**15:26.614** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:20.437 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:00.294 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:26.863 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:19.565 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.861 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.733 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.340 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.399 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:17.452 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:27.940 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.225 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.645 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.816 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.851 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.161 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.172 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.005 | 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_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_install.py` (``install.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 60ddb6233f..842e55161e 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,7 +294,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000007
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000007
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.816790000561014e-06 1.0
- naive 6.6958e-06 0.8565920281240049
- parallel 7.8228e-06 1.0007688577329767
- vector 2.45895e-05 3.1457286172757875
+ numpy 7.027849999303726e-06 1.0
+ naive 6.690799999999999e-06 0.9520408091611061
+ parallel 6.907099999999999e-06 0.9828183584857829
+ vector 2.4627699999999998e-05 3.504300746663624
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017941
+ Numpy running time: 0.018532
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.484754
+ none: 3.446846
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.298115
+ blocking: 0.317329
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.340272
+ vectorization: 0.338907
@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, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.113986
+ loop permutation: 0.116947
@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, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108164
+ array packing: 0.107417
@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, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110795
+ block caching: 0.111772
@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, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146664
+ parallelization: 0.146946
@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, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4847542624 1.0
- blocking 0.29811537239999997 0.08554846337850051
- vectorization 0.34027210599999996 0.09764594010874376
- loop permutation 0.1139862972 0.03270999577499505
- array packing 0.1081643957 0.03103931799928573
- block caching 0.11079468300000002 0.031794116502118615
- parallelization 0.146663753 0.04208725837069228
+ none 3.4468455435000003 1.0
+ blocking 0.31732924469999996 0.09206366827153419
+ vectorization 0.3389065962 0.09832369681870545
+ loop permutation 0.1169471114 0.033928735687195725
+ array packing 0.10741658950000002 0.031163737435976585
+ block caching 0.1117716621 0.032427232578140036
+ parallelization 0.14694571350000002 0.04263194031920218
@@ -1654,7 +1654,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.861 seconds)
+ **Total running time of the script:** ( 1 minutes 1.733 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 96114bede8..0cc00d695d 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-02820ad283077c54d257b9384998c8e94821a296
+0dc26dd87052ca7c0245a9eb26110e83a96982b1
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index b71d551d95..5b09f631f2 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -579,7 +579,7 @@ 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 9.091 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.719 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index a1efe5bf6f..bdedd83afc 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -500,7 +500,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 965ms/step
+1/1 [==============================] - 1s 977ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 7f75be6292..6704623f33 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -434,7 +434,7 @@ 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.zip7597c36c-3b55-47ff-afa1-414479fd7846 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.zip2bbcb9c0-7828-4717-8c9f-cbb479489188 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 d8abae3aea..d0c1c6a104 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -442,13 +442,12 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 51.3MB/s]
- 36%|###6 | 14.9M/41.5M [00:00<00:00, 61.4MB/s]
- 51%|#####1 | 21.3M/41.5M [00:00<00:00, 63.5MB/s]
- 66%|######6 | 27.5M/41.5M [00:00<00:00, 50.9MB/s]
- 82%|########2 | 34.1M/41.5M [00:00<00:00, 55.3MB/s]
- 96%|#########5| 39.7M/41.5M [00:00<00:00, 47.8MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 51.5MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 39.7MB/s]
+ 36%|###5 | 14.9M/41.5M [00:00<00:00, 52.8MB/s]
+ 54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.7MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.9MB/s]
+ 93%|#########2| 38.4M/41.5M [00:00<00:00, 59.2MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 58.5MB/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 a70fd49a44..2a270d8758 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -425,11 +425,10 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 21%|##1 | 9.55M/44.7M [00:00<00:00, 100MB/s]
- 43%|####2 | 19.1M/44.7M [00:00<00:00, 91.9MB/s]
- 62%|######2 | 27.9M/44.7M [00:00<00:00, 90.4MB/s]
- 82%|########1 | 36.5M/44.7M [00:00<00:00, 86.1MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 73.1MB/s]
+ 30%|##9 | 13.2M/44.7M [00:00<00:00, 135MB/s]
+ 58%|#####8 | 26.1M/44.7M [00:00<00:00, 113MB/s]
+ 83%|########2 | 37.1M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 102MB/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 b06a4c5dd2..783ce2b359 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -639,7 +639,7 @@ 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 11.679 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.403 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 9180a5222f..04d60c88e2 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>05:41.355</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:49.430</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -343,43 +343,43 @@
</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>01:11.679</p></td>
+<td><p>01:13.403</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>01:09.091</p></td>
+<td><p>01:09.719</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>00:46.712</p></td>
+<td><p>00:48.304</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>00:31.789</p></td>
+<td><p>00:32.878</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>00:28.717</p></td>
+<td><p>00:29.640</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:26.011</p></td>
+<td><p>00:27.350</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.561</p></td>
+<td><p>00:25.470</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>00:22.232</p></td>
+<td><p>00:22.861</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>00:17.154</p></td>
+<td><p>00:17.361</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>00:02.443</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index fec17702bf..4128c7548a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -913,7 +913,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2756.7223 2755.7563 2764.4060 2754.1772 2.8380
+ 2757.3848 2756.3835 2761.8029 2755.1545 2.3504
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 9799ced2b3..34b092fa7c 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -655,7 +655,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6641 15.5366 16.7499 15.5040 0.3634
+ 16.5177 16.5123 17.3127 15.8657 0.4537
</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 bff0381954..ccdb6fa8d6 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -447,30 +447,29 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 5%|4 | 7.99M/170M [00:00<00:03, 55.1MB/s]
- 9%|8 | 14.5M/170M [00:00<00:02, 61.4MB/s]
- 12%|#2 | 20.5M/170M [00:00<00:03, 52.2MB/s]
- 15%|#5 | 25.6M/170M [00:00<00:03, 49.2MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:03, 46.8MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 54.2MB/s]
- 28%|##8 | 48.1M/170M [00:00<00:02, 62.2MB/s]
- 32%|###1 | 54.3M/170M [00:01<00:02, 56.6MB/s]
- 35%|###5 | 59.9M/170M [00:01<00:02, 53.1MB/s]
- 39%|###8 | 66.0M/170M [00:01<00:01, 55.9MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:02, 50.2MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 47.2MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 53.6MB/s]
- 56%|#####5 | 94.3M/170M [00:01<00:01, 54.1MB/s]
- 60%|###### | 102M/170M [00:01<00:01, 60.5MB/s]
- 64%|######3 | 108M/170M [00:02<00:01, 59.4MB/s]
- 67%|######7 | 114M/170M [00:02<00:00, 59.3MB/s]
- 72%|#######1 | 122M/170M [00:02<00:00, 65.9MB/s]
- 78%|#######8 | 133M/170M [00:02<00:00, 79.3MB/s]
- 83%|########2 | 141M/170M [00:02<00:00, 78.5MB/s]
- 87%|########7 | 148M/170M [00:02<00:00, 73.3MB/s]
- 94%|#########4| 160M/170M [00:02<00:00, 85.4MB/s]
- 99%|#########8| 168M/170M [00:02<00:00, 70.1MB/s]
-100%|##########| 170M/170M [00:02<00:00, 61.4MB/s]
+ 4%|3 | 6.57M/170M [00:00<00:02, 68.9MB/s]
+ 8%|7 | 13.1M/170M [00:00<00:04, 39.0MB/s]
+ 10%|# | 17.5M/170M [00:00<00:04, 33.6MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:03, 39.9MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:04, 33.4MB/s]
+ 24%|##3 | 40.5M/170M [00:01<00:03, 44.5MB/s]
+ 28%|##8 | 48.0M/170M [00:01<00:02, 51.8MB/s]
+ 34%|###3 | 57.1M/170M [00:01<00:01, 62.3MB/s]
+ 38%|###7 | 64.1M/170M [00:01<00:01, 60.4MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 55.2MB/s]
+ 49%|####8 | 82.5M/170M [00:01<00:01, 67.9MB/s]
+ 53%|#####2 | 89.7M/170M [00:01<00:01, 62.8MB/s]
+ 59%|#####9 | 100M/170M [00:01<00:00, 74.3MB/s]
+ 64%|######3 | 108M/170M [00:01<00:00, 74.9MB/s]
+ 68%|######8 | 116M/170M [00:02<00:00, 70.5MB/s]
+ 72%|#######2 | 123M/170M [00:02<00:00, 65.7MB/s]
+ 76%|#######6 | 129M/170M [00:02<00:00, 56.6MB/s]
+ 81%|######## | 137M/170M [00:02<00:00, 61.7MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 60.1MB/s]
+ 91%|######### | 154M/170M [00:02<00:00, 72.2MB/s]
+ 96%|#########5| 162M/170M [00:02<00:00, 75.2MB/s]
+100%|#########9| 170M/170M [00:02<00:00, 71.1MB/s]
+100%|##########| 170M/170M [00:02<00:00, 59.6MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -568,7 +567,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 10.770 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.953 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 4c6256930d..9b23467dff 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -491,8 +491,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 61.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 77.7MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 49.5MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 64.7MB/s]
</pre></div>
</div>
</div>
@@ -583,7 +583,7 @@ 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)
- 90.3064 90.2467 92.4185 89.9342 0.3119
+ 90.3028 90.2496 91.1758 90.0903 0.1739
</pre></div>
</div>
<div class="admonition note">
@@ -622,7 +622,7 @@ 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 4.988 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.203 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 bac9ecd32f..983dddab3b 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -576,7 +576,7 @@ 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)
- 119.1475 119.1158 121.0518 117.8614 0.5495
+ 120.6204 120.4145 125.5072 119.7050 0.8173
</pre></div>
</div>
<div class="admonition note">
@@ -604,7 +604,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.127 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.181 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 ccc6a5dffe..b10bf206ba 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -514,7 +514,7 @@ 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 29.041 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.307 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 dd5388111a..1e9dc94f90 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -456,22 +456,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6187/132723 [00:00<00:02, 61858.41KB/s]
- 11%|#1 | 14904/132723 [00:00<00:01, 76741.52KB/s]
- 18%|#7 | 23667/132723 [00:00<00:01, 81711.57KB/s]
- 24%|##4 | 32472/132723 [00:00<00:01, 84212.37KB/s]
- 31%|###1 | 41322/132723 [00:00<00:01, 85754.50KB/s]
- 38%|###7 | 50137/132723 [00:00<00:00, 86560.88KB/s]
- 44%|####4 | 58794/132723 [00:00<00:00, 86212.61KB/s]
- 51%|##### | 67664/132723 [00:00<00:00, 86999.16KB/s]
- 58%|#####7 | 76488/132723 [00:00<00:00, 87384.37KB/s]
- 64%|######4 | 85320/132723 [00:01<00:00, 87670.21KB/s]
- 71%|####### | 94088/132723 [00:01<00:00, 87598.90KB/s]
- 78%|#######7 | 102942/132723 [00:01<00:00, 87882.69KB/s]
- 84%|########4 | 111770/132723 [00:01<00:00, 87999.92KB/s]
- 91%|######### | 120623/132723 [00:01<00:00, 88157.66KB/s]
- 98%|#########7| 129465/132723 [00:01<00:00, 88233.43KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 86156.69KB/s]
+ 5%|5 | 6824/132723 [00:00<00:01, 68233.23KB/s]
+ 12%|#1 | 15267/132723 [00:00<00:01, 77748.73KB/s]
+ 17%|#7 | 23042/132723 [00:00<00:01, 76220.29KB/s]
+ 24%|##3 | 31568/132723 [00:00<00:01, 79743.76KB/s]
+ 30%|##9 | 39583/132723 [00:00<00:01, 79722.45KB/s]
+ 36%|###5 | 47777/132723 [00:00<00:01, 80468.62KB/s]
+ 42%|####2 | 56289/132723 [00:00<00:00, 81979.08KB/s]
+ 49%|####8 | 64879/132723 [00:00<00:00, 83221.84KB/s]
+ 55%|#####5 | 73457/132723 [00:00<00:00, 84015.96KB/s]
+ 62%|######1 | 81920/132723 [00:01<00:00, 84201.93KB/s]
+ 68%|######8 | 90478/132723 [00:01<00:00, 84621.66KB/s]
+ 75%|#######4 | 99091/132723 [00:01<00:00, 85078.59KB/s]
+ 81%|########1 | 107600/132723 [00:01<00:00, 85028.73KB/s]
+ 88%|########7 | 116205/132723 [00:01<00:00, 85332.80KB/s]
+ 94%|#########3| 124739/132723 [00:01<00:00, 85210.63KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 82922.55KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -510,7 +510,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.381 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 9.149 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 a3e16b2d7c..6f08c7f6ba 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>13:33.991</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:59.606</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -343,43 +343,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:10.770</p></td>
+<td><p>03:20.953</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>03:02.381</p></td>
+<td><p>03:09.149</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:28.127</p></td>
+<td><p>02:30.181</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>01:29.041</p></td>
+<td><p>01:29.307</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>01:04.988</p></td>
+<td><p>01:07.203</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:53.608</p></td>
+<td><p>00:54.648</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:34.764</p></td>
+<td><p>00:36.511</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.295</p></td>
+<td><p>00:26.069</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>00:25.010</p></td>
+<td><p>00:25.578</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>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 781c0f6249..e3119e6130 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -615,7 +615,7 @@ 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.zip0b6fb6ef-1aeb-43c2-aa45-6d46452efb0c 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.zip76c65472-fc65-49aa-a489-ce354f6179e2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index ba84ce4ed8..a04db68644 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>00:46.602</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:48.669</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -343,19 +343,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:43.219</p></td>
+<td><p>00:45.182</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>00:02.364</p></td>
+<td><p>00:02.441</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.010</p></td>
+<td><p>00:01.040</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 9b0f43e220..4fb069e28d 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -519,10 +519,10 @@ 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: 7150us [7150us] (46.29%; 46.29%)
-FoldScaleAxis: 8296us [7us] (53.71%; 53.71%)
- FoldConstant: 8290us [1727us] (53.67%; 99.92%)
- InferType: 6563us [6563us] (42.49%; 79.17%)
+InferType: 7219us [7219us] (46.78%; 46.78%)
+FoldScaleAxis: 8212us [7us] (53.22%; 53.22%)
+ FoldConstant: 8205us [1646us] (53.18%; 99.92%)
+ InferType: 6559us [6559us] (42.51%; 79.94%)
</pre></div>
</div>
</div>
@@ -544,10 +544,10 @@ 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: 6553us [6553us] (44.83%; 44.83%)
-FoldScaleAxis: 8065us [5us] (55.17%; 55.17%)
- FoldConstant: 8061us [1661us] (55.14%; 99.94%)
- InferType: 6399us [6399us] (43.77%; 79.39%)
+InferType: 6662us [6662us] (45.01%; 45.01%)
+FoldScaleAxis: 8141us [5us] (54.99%; 54.99%)
+ FoldConstant: 8136us [1658us] (54.96%; 99.94%)
+ InferType: 6477us [6477us] (43.76%; 79.62%)
</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 d800492047..fe7691ccb0 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -571,7 +571,7 @@ 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: 33.136703 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 43.125183 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 f47f98531c..7a6f736292 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -908,7 +908,7 @@ 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: 13.343097 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.843904 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 e6fb43b087..0c0dafd719 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -468,8 +468,8 @@ 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: 0.017760
-Baseline: 3.483428
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018469
+Baseline: 3.462473
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -528,7 +528,7 @@ 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: 0.293434
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.303435
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ 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: 0.329534
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.342679
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -654,7 +654,7 @@ 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: 0.114359
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115973
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -736,7 +736,7 @@ 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: 0.109011
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108151
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -821,7 +821,7 @@ 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: 0.110742
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112048
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -910,7 +910,7 @@ 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: 0.146781
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147245
</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 8e74afde99..0ab734ad44 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>00:34.792</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.117</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -343,15 +343,15 @@
</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>00:32.254</p></td>
+<td><p>00:32.553</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>00:01.506</p></td>
+<td><p>00:01.519</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>00:01.032</p></td>
+<td><p>00:01.045</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 8fe191bfbb..deda5f4882 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -334,7 +334,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:14.009</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:00.008</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -343,27 +343,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:39.545</p></td>
+<td><p>05:32.717</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>01:31.230</p></td>
+<td><p>01:33.182</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:01.126</p></td>
+<td><p>01:02.291</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>00:39.281</p></td>
+<td><p>00:28.507</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:11.845</p></td>
+<td><p>00:12.130</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:10.983</p></td>
+<td><p>00:11.180</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 6f50f5111f..226b6c1435 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
@@ -497,11 +497,11 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -516,778 +516,463 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ for (rc.outer.outer: int32, 0, 64) {
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_2: int32 = (rc.outer.outer*72)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[((((((blockIdx.x*294912) + (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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 161280)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 193536)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 225792)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4928), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5152), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel_3[(((((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5600), 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" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel_3[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5824), 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" = 224;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel_3[((((((blockIdx.x*294912) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 290304)]
- }
- for (ff.outer.inner: int32, 0, 2) {
- let cse_var_11: int32 = (ff.outer.inner*7)
- let cse_var_10: int32 = (cse_var_11 + 6)
- let cse_var_9: int32 = (cse_var_11 + 5)
- let cse_var_8: int32 = (cse_var_11 + 4)
- let cse_var_7: int32 = (cse_var_11 + 3)
- let cse_var_6: int32 = (cse_var_11 + 2)
- let cse_var_5: int32 = (cse_var_11 + 1)
- {
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96))]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 1)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 2)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 3)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 4)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 5)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 6)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 7)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 8)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 9)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 10)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 11)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 12)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 13)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 14)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 15)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 16)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 17)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 18)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 19)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 20)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 21)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 22)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 23)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 24)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 25)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 26)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 27)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 28)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 29)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 633)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 634)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 635)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 636)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 30)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 631)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 633)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 634)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 635)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 636)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 31)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 632)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 633)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 634)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 635)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 636)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 32)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 696)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 697)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 698)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 699)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 33)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 696)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 697)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 698)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 699)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 34)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 696)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 697)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 698)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 699)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 35)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 759)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 760)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 761)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 762)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 36)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 759)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 760)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 761)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 762)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 37)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 759)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 760)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 761)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 762)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 38)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 39)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 40)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 41)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 885)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 886)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 887)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 888)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 42)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 883)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 885)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 886)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 887)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 888)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 43)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 884)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 885)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 886)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 887)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 888)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 44)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 948)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 949)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 950)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 951)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 45)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 948)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 949)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 950)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 951)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 46)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 948)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 949)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 950)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 951)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 47)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1011)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1012)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1013)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1014)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 48)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1011)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1012)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1013)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1014)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 49)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1011)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1012)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1013)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1014)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1016)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 50)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 51)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 52)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1079)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 53)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 54)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 55)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1142)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 56)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1201)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1202)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 57)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1201)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1202)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 58)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1201)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1202)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1205)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 59)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 60)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 61)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 62)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 63)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 64)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1327)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1328)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1331)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 65)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1390)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1391)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 66)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1387)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1390)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1391)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 67)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1388)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1389)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1390)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1391)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1394)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 68)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1453)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1454)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 69)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1453)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1454)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 70)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1453)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1454)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1457)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 71)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1516)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1517)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 72)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1516)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1517)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 73)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1516)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1517)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1520)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 74)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1579)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1580)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 75)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1579)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1580)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 76)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1579)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1580)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1583)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 77)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1640)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1641)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1642)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1643)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 78)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1639)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1640)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1641)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1642)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1643)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 79)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1640)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1641)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1642)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1643)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1646)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 80)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1705)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1706)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 81)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1705)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1706)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 82)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1705)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1706)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1709)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 83)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1768)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1769)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 84)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1768)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1769)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 85)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1768)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1769)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1772)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 86)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1831)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1832)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 87)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1831)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1832)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 88)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1831)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1832)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1835)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 89)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1894)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1895)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 90)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1894)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1895)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 91)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1894)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1895)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1898)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 92)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1955)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1956)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1957)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1958)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 93)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1954)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1955)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1956)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1957)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1958)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 94)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1955)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1956)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1957)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1958)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1961)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (ff.outer.inner*96)) + 95)]))
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.out [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], [...]
}
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
for (i1.inner: int32, 0, 2) {
for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1325,7 +1010,7 @@ 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: 0.428 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.352 ms
</pre></div>
</div>
</div>
@@ -1356,31 +1041,31 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_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=32)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_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)
+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)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
@@ -1403,14 +1088,14 @@ 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=224)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
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=224)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1428,10 +1113,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[6144];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1446,728 +1131,411 @@ extern "C" __global__ void __launch_bounds__(224) default_function_ker
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 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) + 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) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 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) + 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) + 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) + 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) + 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) + 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) + 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);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 672)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 1344)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 2016)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((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) + 2688)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 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) + 3360)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 161280)];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 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) + 4032)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 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) + 4704)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 225792)];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4928) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5152) / 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) + 5376)] = kernel[(((((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5600) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5824) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 96) {
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[((((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 290304)];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
}
- __syncthreads();
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96))]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 1)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 2)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 3)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 4)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 5)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 6)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 7)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 8)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 9)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 10)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 11)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 12)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 13)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 14)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 15)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 16)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 17)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 18)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 19)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 20)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 21)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 22)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 23)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 24)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 25)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 26)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 27)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 28)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 29)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 30)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 31)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 32)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 33)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 34)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 35)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 36)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 37)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 38)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 39)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 40)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 41)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 42)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 43)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 44)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 45)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 46)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 47)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1011)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1012)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1013)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1014)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 48)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1011)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1012)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1013)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1014)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 49)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1011)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1012)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1013)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1014)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1016)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 50)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 51)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 52)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1079)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 53)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 54)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 55)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1142)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 56)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1201)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1202)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 57)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1201)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1202)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 58)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1201)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1202)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1205)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 59)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 60)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 61)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 62)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 63)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 64)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1327)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1328)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1331)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 65)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1390)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1391)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 66)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1390)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1391)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 67)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1390)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1391)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1394)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 68)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1453)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1454)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 69)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1453)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1454)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 70)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1453)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1454)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1457)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 71)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1516)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1517)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 72)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1516)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1517)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 73)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1516)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1517)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1520)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 74)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1579)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1580)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 75)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1579)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1580)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 76)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1579)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1580)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1583)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 77)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1640)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1641)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1642)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1643)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 78)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1639)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1640)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1641)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1642)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1643)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 79)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1640)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1641)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1642)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1643)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1646)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 80)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1705)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1706)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 81)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1705)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1706)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 82)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1705)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1706)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1709)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 83)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1768)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1769)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 84)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1768)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1769)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 85)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1768)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1769)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1772)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 86)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1831)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1832)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 87)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1831)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1832)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 88)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1831)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1832)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1835)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 89)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1894)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1895)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 90)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1894)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1895)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 91)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1894)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1895)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1898)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 92)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1955)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1956)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1957)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1958)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 93)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1954)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1955)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1956)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1957)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1958)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 94)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1955)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1956)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1957)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1958)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1961)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (ff_outer_inner * 96)) + 95)]));
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -2205,7 +1573,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 39.545 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 32.717 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 c975b1172f..c8035d8f24 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -909,7 +909,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8673 7.8628 7.8774 7.8617 0.0071
+ 7.8822 7.8840 7.8845 7.8781 0.0029
</pre></div>
</div>
</div>
@@ -931,7 +931,7 @@ 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 1.126 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.291 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index fbb218ddfc..f3e518c22e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -928,7 +928,7 @@ 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)
- 749.7118 749.4310 752.3175 747.3870 2.0226
+ 783.9181 784.3521 784.7166 782.6856 0.8841
</pre></div>
</div>
</div>
@@ -950,7 +950,7 @@ 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 31.230 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.182 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 b5f5b36d8f..fc35411f67 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -626,14 +626,13 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer: int32, 0, 4) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- 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))
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
{
- compute_4: Buffer(compute_3, float32, [1024], [])[cse_var_1] = 0f32
+ compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
compute_4[(cse_var_1 + 1)] = 0f32
compute_4[(cse_var_1 + 2)] = 0f32
compute_4[(cse_var_1 + 3)] = 0f32
@@ -651,51 +650,81 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_4[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_19: int32 = ((i0.outer*8192) + (i.inner*256))
- let cse_var_18: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
{
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*128) + (i.inner*16))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_3]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*128) + (i.inner*16)) + 1)
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*128) + (i.inner*16)) + 2)
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*128) + (i.inner*16)) + 3)
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*128) + (i.inner*16)) + 4)
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*128) + (i.inner*16)) + 5)
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*128) + (i.inner*16)) + 6)
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*128) + (i.inner*16)) + 7)
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*128) + (i.inner*16)) + 8)
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*128) + (i.inner*16)) + 9)
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*128) + (i.inner*16)) + 10)
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*128) + (i.inner*16)) + 11)
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*128) + (i.inner*16)) + 12)
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*128) + (i.inner*16)) + 13)
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*128) + (i.inner*16)) + 14)
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_3 + 1)] - placeholder_15[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*16)) + 15)
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_20, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -733,7 +762,7 @@ 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: 1.779 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.846 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 3b894b33a4..95d293df66 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>00:24.122</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:39.498</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -343,22 +343,22 @@
</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>00:24.087</p></td>
+<td><p>00:39.459</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.023</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>
<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="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 3efac9ea2b..af6ccffc6e 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -683,7 +683,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,893513
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4644417
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -806,10 +806,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6803258
-No: 3 GFLOPS: 18.48/18.48 result: MeasureResult(costs=(0.012530515625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.823655366897583, timestamp=1670587331.8632438) [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6425064
-No: 4 GFLOPS: 77.10/77.10 result: MeasureResult(costs=(0.003002456411764706,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7681941986083984, timestamp=1670587333.4850144) [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6595849
-No: 5 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,903192
+No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -931,8 +929,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4389549
-No: 6 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8540490
+No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1054,8 +1052,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,330947
-No: 7 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4724827
+No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1177,9 +1175,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,302787
-No: 8 GFLOPS: 59.19/77.10 result: MeasureResult(costs=(0.0039114751,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9455833435058594, timestamp=1670587336.5763662) [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9297684
-No: 9 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7549074
+No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1301,8 +1298,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,527802
-No: 10 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1135677
+No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1424,8 +1421,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2926683
-No: 11 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7032174
+No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1547,8 +1544,26 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7508028
-No: 12 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 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,2824912
+No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7010017
+No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1670,8 +1685,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1773814
-No: 13 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6313242
+No: 11 GFLOPS: 119.62/119.62 result: MeasureResult(costs=(0.0019353803461538465,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2919700145721436, timestamp=1670649520.2961972) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,265341
+No: 12 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1793,8 +1809,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3793952
-No: 14 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2569313
+No: 13 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1916,8 +1932,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,627215
-No: 15 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3029567
+No: 14 GFLOPS: 17.61/119.62 result: MeasureResult(costs=(0.013147758444444444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1835360527038574, timestamp=1670649522.7851512) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1035992
+No: 15 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2039,8 +2056,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7915996
-No: 16 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7932968
+No: 16 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2162,131 +2179,161 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1077301
-No: 17 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1559113
+No: 17 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f8228d11fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h:1617
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,280042
-No: 18 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
+
+Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,778906
+No: 18 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2408,8 +2455,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8470241
-No: 19 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1873653
+No: 19 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2531,8 +2578,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('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, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3321273
-No: 20 GFLOPS: 0.00/77.10 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8099382
+No: 20 GFLOPS: 0.00/119.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2654,7 +2701,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3079062
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4599615
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2693,9 +2740,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6595849
+[('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,265341
Finish loading 20 records
-Time cost of this operator: 0.003391
+Time cost of this operator: 0.001146
</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 a35ebe0796..e788bd5cb7 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -592,10 +592,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.6 98.723 (1, 2, 10, 10, 3) 2 1 [311.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.97 (1, 6, 10, 10) 1 1 [3.063]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.307 (1, 1, 10, 10, 3) 1 1 [0.969]
-Total_time - 315.632 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.3 98.73 (1, 2, 10, 10, 3) 2 1 [311.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.958 (1, 6, 10, 10) 1 1 [3.021]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.312 (1, 1, 10, 10, 3) 1 1 [0.983]
+Total_time - 315.304 - - - - -
</pre></div>
</div>
</div>
@@ -647,10 +647,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.4 97.49 (1, 6, 10, 10, 1) 2 1 [103.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.693 (1, 6, 10, 10) 1 1 [1.795]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.867 0.817 (1, 3, 10, 10, 1) 1 1 [0.867]
-Total_time - 106.062 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 136.2 98.108 (1, 6, 10, 10, 1) 2 1 [136.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.277 (1, 6, 10, 10) 1 1 [1.773]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.853 0.614 (1, 3, 10, 10, 1) 1 1 [0.853]
+Total_time - 138.826 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 799ae18dc9..07a6aaa60e 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -434,8 +434,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 61%|###### | 2.09M/3.42M [00:00<00:00, 18.1MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 28.2MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 51.0MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -559,7 +558,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.099 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.132 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 1b5ebd6c78..5ad4f6ac68 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -524,7 +524,7 @@ 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/tmpgzkadn12/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmprtqcm2s5/images/random'
</pre></div>
</div>
</div>
@@ -584,8 +584,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpgzkadn12/images/target contains 8144 images
-/tmp/tmpgzkadn12/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmprtqcm2s5/images/target contains 8144 images
+/tmp/tmprtqcm2s5/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -697,13 +697,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 46s - loss: 0.2280 - accuracy: 0.9195 - val_loss: 0.1161 - val_accuracy: 0.9592 - 46s/epoch - 141ms/step
+328/328 - 47s - loss: 0.2191 - accuracy: 0.9222 - val_loss: 0.1461 - val_accuracy: 0.9532 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0994 - accuracy: 0.9630 - val_loss: 0.0944 - val_accuracy: 0.9679 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0951 - accuracy: 0.9648 - val_loss: 0.1402 - val_accuracy: 0.9573 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0676 - accuracy: 0.9740 - val_loss: 0.1067 - val_accuracy: 0.9675 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0672 - accuracy: 0.9764 - val_loss: 0.1104 - val_accuracy: 0.9626 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f6048763290>
+<keras.callbacks.History object at 0x7f7d19fe6190>
</pre></div>
</div>
</div>
@@ -965,7 +965,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 32.704 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 22.951 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 f04fe9b09e..80186ee20c 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>06:35.849</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:30.856</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -343,23 +343,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:32.704</p></td>
+<td><p>04:22.951</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:02.099</p></td>
+<td><p>01:04.132</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:49.627</p></td>
+<td><p>00:52.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.674</p></td>
+<td><p>00:07.880</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>00:03.741</p></td>
+<td><p>00:03.882</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></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 b9ede15dba..7d03b93549 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>00:44.245</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:45.978</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -343,15 +343,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.174</p></td>
+<td><p>00:33.420</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.402</p></td>
+<td><p>00:10.766</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.661</p></td>
+<td><p>00:01.785</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 44e0a4be63..2cdab6da65 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -529,7 +529,7 @@ 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 0x7f60475ec050>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f7d1ac2a440>
</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 806c5f32ae..85df4c0ed8 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -334,7 +334,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:08.130</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.863</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -343,23 +343,23 @@
</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>00:05.681</p></td>
+<td><p>00:06.242</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.108</p></td>
+<td><p>00:01.241</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>00:00.574</p></td>
+<td><p>00:00.594</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>00:00.554</p></td>
+<td><p>00:00.567</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>00:00.112</p></td>
+<td><p>00:00.114</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -367,11 +367,11 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.031</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.023</p></td>
+<td><p>00:00.024</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 24a660c992..2243cb0a83 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -580,7 +580,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_a64hl4d/input0.cc'\nsource_filename = \"/tmp/tmp_a64hl4d/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/tmpbjrmmd8z/input0.cc'\nsource_filename = \"/tmp/tmpbjrmmd8z/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 cb03d98ee9..efe4deb201 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1609,7 +1609,7 @@ 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>
@@ -1893,7 +1893,7 @@ 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 ef6e3fc15f..d4a2fe1df6 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/02820ad28/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 b279ef6e4e..32dfdda9aa 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/02820ad28/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 2a382eca33..f68013c4eb 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/02820ad28/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 8f209cf91c..dabea323eb 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/02820ad28/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 8310979094..2ef560902a 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/02820ad28/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 5d31e8a7fd..47938ccf13 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/02820ad28/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 52f2d3f068..d94e5c4a74 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/02820ad28/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 79ed705c7d..5a21a5482b 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/02820ad28/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/02820ad28/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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 433be8997e..b60e940b02 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/02820ad28/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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/02820ad28/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0dc26dd87/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>
... 2080 lines suppressed ...